{"id":51566,"url":"https://github.com/ChanChiChoi/awesome-model-compression","name":"awesome-model-compression","description":"papers about model compression","projects_count":961,"last_synced_at":"2026-10-21T21:00:27.066Z","repository":{"id":49300301,"uuid":"174922922","full_name":"ChanChiChoi/awesome-model-compression","owner":"ChanChiChoi","description":"papers about model compression","archived":false,"fork":false,"pushed_at":"2023-02-10T09:58:06.000Z","size":516,"stargazers_count":166,"open_issues_count":0,"forks_count":37,"subscribers_count":10,"default_branch":"main","last_synced_at":"2026-10-02T15:53:46.294Z","etag":null,"topics":["model-compression"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ChanChiChoi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2019-03-11T03:59:54.000Z","updated_at":"2025-11-19T11:19:27.000Z","dependencies_parsed_at":"2024-01-19T17:05:12.528Z","dependency_job_id":"44300c52-e018-4fc9-8a20-4784081f52c4","html_url":"https://github.com/ChanChiChoi/awesome-model-compression","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ChanChiChoi/awesome-model-compression","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChanChiChoi%2Fawesome-model-compression","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChanChiChoi%2Fawesome-model-compression/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChanChiChoi%2Fawesome-model-compression/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChanChiChoi%2Fawesome-model-compression/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChanChiChoi","download_url":"https://codeload.github.com/ChanChiChoi/awesome-model-compression/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChanChiChoi%2Fawesome-model-compression/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":344956071,"owners_count":38449333,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-10-03T21:59:58.778Z","status":"online","status_checked_at":"2026-10-21T02:00:07.576Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-01-14T11:16:23.504Z","updated_at":"2026-10-21T21:00:27.066Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["PAPERS","LIBRARIES","BLOGS \u0026 ATRICLES","PROJECTS","REFERENCE","OTHERS"],"sub_categories":["2017","2018","2014","2016","2015","2023","2019","1990","1998","2006","1993","1997","2000","2001","2011","2013","1995"],"readme":"\n# awesome-model-compression\n\nthis collecting the papers (main from arxiv.org) about Model compression:    \n**Structure**;   \n**Distillation**;   \n**Binarization**;   \n**Quantization**;   \n**Pruning**;   \n**Low Rank**.  \n\n---\n# CONTENT\n[PAPERS](https://github.com/ChanChiChoi/awesome-model-compression#papers)  \n[BOOKS](https://github.com/ChanChiChoi/awesome-model-compression#books)  \n[BLOGS\u0026ATRICLES](https://github.com/ChanChiChoi/awesome-model-compression#blogs--atricles)  \n[LIBRARIES](https://github.com/ChanChiChoi/awesome-model-compression#libraries)  \n[PROJECTS](https://github.com/ChanChiChoi/awesome-model-compression#projects)  \n[OTHERS](https://github.com/ChanChiChoi/awesome-model-compression#others)  \n[REFERENCE](https://github.com/ChanChiChoi/awesome-model-compression#REFERENCE)  \n\n---\n## PAPERS\n\n### 1990\n- 【Pruning】 LeCun Y, Denker J S, Solla S A. [Optimal brain damage](http://papers.nips.cc/paper/250-optimal-brain-damage.pdf) .[C]//Advances in neural information processing systems. 1990: 598-605.\n- 【Distillation】[Neural Network Ensembles](https://www.researchgate.net/publication/3191841_Neural_Network_Ensembles), L.K. Hansen, P. Salamon, 1990\n\n\n### 1993\n- Hassibi, Babak, and David G. Stork. [Second order derivatives for network pruning: Optimal brain surgeon](http://papers.nips.cc/paper/647-second-order-derivatives-for-network-pruning-optimal-brain-surgeon.pdf) .[C]Advances in neural information processing systems. 1993.\n- J. L. Holi and J. N. Hwang. [Finite precision error analysis of neural network hardware implementations]. In Ijcnn-91- Seattle International Joint Conference on Neural Networks, pages 519–525 vol.1, 1993. \n\n  \n### 1995\n- 【Distillation】[Neural Network Ensembles, Cross Validation, and Active Learning](https://papers.nips.cc/paper/1001-neural-network-ensembles-cross-validation-and-active-learning.pdf), Andres Krogh, Jesper Vedelsby, 1995\n\n### 1997 \n- [Knowledge Acquisition from Examples Via Multiple Models](https://homes.cs.washington.edu/~pedrod/papers/mlc97.pdf), Perdo Domingos, 1997\n\n### 1998\n- 【distillation】[Combining labeled and unlabeled data with co-training](https://www.cs.cmu.edu/~avrim/Papers/cotrain.pdf), A. Blum, T. Mitchell, 1998\n\n\n### 2000\n- 【Distillation】[Ensemble Methods in Machine Learning](http://web.engr.oregonstate.edu/~tgd/publications/mcs-ensembles.pdf), Thomas G. Dietterich, 2000\n- [Using A Neural Network to Approximate An Ensemble of Classifiers](http://axon.cs.byu.edu/papers/zeng.npl2000.pdf), Xinchuan Zeng and Tony R. Martinez, 2000\n\n### 2001\n- Suzuki, Kenji, Isao Horiba, and Noboru Sugie. [A simple neural network pruning algorithm with application to filter synthesis](https://link.springer.com/article/10.1023/A:1009639214138) .[C] Neural Processing Letters 13.1 (2001): 43-53.. 2001\n\n  \n### 2006\n- 【Distillation】[Model Compression](http://www.cs.cornell.edu/~caruana/compression.kdd06.pdf), Rich Caruana, 2006\n\n\n### 2011\n- 【Quantization】 Jegou, Herve, Matthijs Douze, and Cordelia Schmid. [Product quantization for nearest neighbor search](https://hal.inria.fr/inria-00514462/document) IEEE transactions on pattern analysis and machine intelligence 33.1 (2011): 117-128.\n- 【Quantization】Vanhoucke V, Senior A, Mao M Z. [Improving the speed of neural networks on CPUs](https://ai.google/research/pubs/pub37631.pdf)[J]. 2011.\n\n### 2012\n- D. Hammerstrom. [A vlsi architecture for highperformance, low-cost, on-chip learning]. In IJCNN International Joint Conference on Neural Networks, pages 537– 544 vol.2, 2012.\n\n\n### 2013\n- M. Denil, B. Shakibi, L. Dinh, N. de Freitas, et al. [Predicting parameters in deep learning](http://papers.nips.cc/paper/5025-predicting-parameters-in-deep-learning.pdf). In Advances in Neural Information Processing Systems, pages 2148–2156, 2013\n- 【Distillation】Mathieu M, Henaff M, LeCun Y. [Fast training of convolutional networks through ffts](https://arxiv.org/pdf/1312.5851)[J]. arXiv preprint arXiv:1312.5851, 2013.\u003cbr\u003e【code:[Maratyszcza/NNPACK](https://github.com/Maratyszcza/NNPACK)】\n- [Do Deep Nets Really Need to be Deep?](https://arxiv.org/pdf/1312.6184.pdf), Lei Jimmy Ba, Rich Caruana, 2013\n\n### 2014\n- K. Hwang and W. Sung. [Fixed-point feedforward deep neural network design using weights+ 1, 0, and- 1]. In 2014 IEEE Workshop on Signal Processing Systems (SiPS), pages 1–6. IEEE, 2014. \n- M. Horowitz. [1.1 computing’s energy problem (and what we can do about it)](https://pdfs.semanticscholar.org/9476/20a1854655ed91a86b90d12695e05be85983.pdf). In Solid-State Circuits Conference Digest of Technical Papers, pages 10–14, 2014. \n- Y. Chen, N. Sun, O. Temam, T. Luo, S. Liu, S. Zhang, L. He, J.Wang, L. Li, and T. Chen. [Dadiannao: A machinelearning supercomputer](http://pages.saclay.inria.fr/olivier.temam/files/eval/supercomputer.pdf). In Ieee/acm International Symposium on Microarchitecture, pages 609–622, 2014.\n- 【Distillation】Hinton, Geoffrey, Oriol Vinyals, and Jeff Dean. [Dark knowledge](http://www.ttic.edu/dl/dark14.pdf) .[C]Presented as the keynote in BayLearn 2 (2014).\n- 【Low Rank】Jaderberg, Max, Andrea Vedaldi, and Andrew Zisserman. [Speeding up convolutional neural networks with low rank expansions](http://www.robots.ox.ac.uk/~vgg/publications/2014/Jaderberg14b/jaderberg14b.pdf) .[J] arXiv preprint arXiv:1405.3866 (2014).\n- 【Low Rank】Emily Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun, Rob Fergus .[Exploiting Linear Structure Within Convolutional Networks for Efficient  Evaluation](https://arxiv.org/pdf/1404.00736) .[J] arXiv preprint arXiv:1404.00736\n- 【Low rank】Jaderberg M, Vedaldi A, Zisserman A. [Speeding up convolutional neural networks with low rank expansions](https://arxiv.org/pdf/1405.3866)[J]. arXiv preprint arXiv:1405.3866, 2014.\n- 【Low Rank】Xiangyu Zhang, Jianhua Zou, Xiang Ming, Kaiming He, Jian Sun .[Efficient and Accurate Approximations of Nonlinear Convolutional  Networks](https://arxiv.org/pdf/1411.04229) .[J] arXiv preprint arXiv:1411.04229\n- 【Distillation】[Learning with Pseudo-Ensembles](https://arxiv.org/pdf/1412.4864.pdf), Philip Bachman, Ouais Alsharif, Doina Precup, 2014\n- 【Structure】 Jin J, Dundar A, Culurciello E. [Flattened convolutional neural networks for feedforward acceleration](https://arxiv.org/pdf/1412.5474) .[J]. arXiv preprint arXiv:1412.5474, 2014.\n- 【Quantization】Yunchao Gong, Liu Liu, Ming Yang, Lubomir Bourdev .[Compressing Deep Convolutional Networks using Vector Quantization](https://arxiv.org/pdf/1412.06115) .[J] arXiv preprint arXiv:1412.06115\n- 【Distillation】driana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, Yoshua Bengio .[FitNets: Hints for Thin Deep Nets](https://arxiv.org/pdf/1412.06550) .[J] arXiv preprint arXiv:1412.06550\n- 【Quantization】[Compressing Deep Convolutional Networks using Vector Quantization](https://arxiv.org/pdf/1412.6115.pdf)\n- 【Low Rank】 Lebedev V, Ganin Y, Rakhuba M, et al. [Speeding-up convolutional neural networks using fine-tuned cp-decomposition](https://arxiv.org/pdf/1412.6553) .[J]. arXiv preprint arXiv:1412.6553, 2014.\u003cbr\u003e【code:[vadim-v-lebedev/cp-decomposition](https://github.com/vadim-v-lebedev/cp-decomposition); [jacobgil/pytorch-tensor-decompositions](https://github.com/jacobgil/pytorch-tensor-decompositions); [medium.com/@keremturgutlu/tensor-decomposition-fast-cnn-in-your-pocket-f03e9b2a6788](https://medium.com/@keremturgutlu/tensor-decomposition-fast-cnn-in-your-pocket-f03e9b2a6788)】\n- 【Quantization】Courbariaux M, Bengio Y, David J P. [Training deep neural networks with low precision multiplications](https://arxiv.org/pdf/1412.7024.pdf))[J]. arXiv preprint arXiv:1412.7024, 2014.\n\n\n### 2015\n- 【Hardware】Dally W. [High-performance hardware for machine learning](https://media.nips.cc/Conferences/2015/tutorialslides/Dally-NIPS-Tutorial-2015.pdf)[J]. NIPS Tutorial, 2015.\n- 【other】Liu B, Wang M, Foroosh H, et al. [Sparse convolutional neural networks](http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Liu_Sparse_Convolutional_Neural_2015_CVPR_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 806-814.\n- Zhang. [Optimizing fpga-based accelerator design for deep convolutional neural networks.] In Proceedings of the 2015 ACM/SIGDA International Symposium on Field- Programmable Gate Arrays, FPGA ’15, 2015. \n- M. Courbariaux, Y. Bengio, and J.-P. David. [Binaryconnect: Training deep neural networks with binary weights during propagations](http://papers.nips.cc/paper/5647-binaryconnect-training-deep-neural-networks-with-binary-weights-during-propagations.pdf). In Advances in Neural Information Processing Systems, pages 3123–3131, 2015.\n- 【System】Lane, Nicholas D., et al. [An Early Resource Characterization of Deep Learning on Wearables, Smartphones and Internet-of-Things Devices](http://niclane.org/pubs/iotapp15_early.pdf) .[C]Proceedings of the 2015 international workshop on internet of things towards applications. ACM, 2015.\n- Han, Song, et al. [Learning both weights and connections for efficient neural network](http://papers.nips.cc/paper/5784-learning-both-weights-and-connections-for-efficient-neural-network) .[C] Advances in neural information processing systems. 2015.\n- 【Low Rank】 Yang Z, Moczulski M, Denil M, et al. [Deep fried convnets](http://openaccess.thecvf.com/content_iccv_2015/papers/Yang_Deep_Fried_Convnets_ICCV_2015_paper.pdf) .[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 1476-1483.\n- 【Structure】 He K, Sun J. [Convolutional neural networks at constrained time cost](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/He_Convolutional_Neural_Networks_2015_CVPR_paper.pdf) .[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 5353-5360.\n- 【Quantization】 Courbariaux, Matthieu, Yoshua Bengio, and Jean-Pierre David. [Binaryconnect: Training deep neural networks with binary weights during propagations.](http://papers.nips.cc/paper/5647-binaryconnect-training-deep-neural-networks-with-binary-weights-during-propagations.pdf) Advances in neural information processing systems. 2015.\n- 【Quantization】Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan, Pritish Narayanan .[Deep Learning with Limited Numerical Precision](https://arxiv.org/pdf/1502.02551) .[J] arXiv preprint arXiv:1502.02551\n- 【Distillation】Geoffrey Hinton, Oriol Vinyals, Jeff Dean .[Distilling the Knowledge in a Neural Network](https://arxiv.org/pdf/1503.02531) .[J] arXiv preprint arXiv:1503.02531\n- Z. Cheng, D. Soudry, Z. Mao, and Z. Lan. [Training binary multilayer neural networks for image classification using expectation backpropagation](https://arxiv.org/pdf/1503.03562). arXiv preprint arXiv:1503.03562, 2015. \n- 【Distillation】[Recurrent Neural Network Training with Dark Knowledge Transfer](https://arxiv.org/pdf/1505.04630.pdf), Zhiyuan Tang, Dong Wang, Zhiyong Zhang, 2015\n- 【Low Rank】Xiangyu Zhang, Jianhua Zou, Kaiming He, Jian Sun .[Accelerating Very Deep Convolutional Networks for Classification and  Detection](https://arxiv.org/pdf/1505.06798) .[J] arXiv preprint arXiv:1505.06798\n- 【Pruning】Song Han, Jeff Pool, John Tran, William J. Dally .[Learning both Weights and Connections for Efficient Neural Networks](https://arxiv.org/pdf/1506.02626) .[J] arXiv preprint arXiv:1506.02626\u003cbr\u003e【code:[jack-willturner/DeepCompression-PyTorch](https://github.com/jack-willturner/DeepCompression-PyTorch)】\n- 【Distillation】[Cross Modal Distillation for Supervision Transfer](https://arxiv.org/pdf/1507.00448), Saurabh Gupta, Judy Hoffman, Jitendra Malik, 2015\n- Srinivas, Suraj, and R. Venkatesh Babu. [Data-free parameter pruning for deep neural networks](https://arxiv.org/abs/1507.06149) .[J] arXiv preprint arXiv:1507.06149\n- 【Pruning】Song Han, Huizi Mao, William J. Dally .[Deep Compression: Compressing Deep Neural Networks with Pruning, Trained  Quantization and Huffman Coding](https://arxiv.org/pdf/1510.00149) .[J] arXiv preprint arXiv:1510.00149\u003cbr\u003e【code:[songhan/Deep-Compression-AlexNet](https://github.com/songhan/Deep-Compression-AlexNet)】\n- 【Distillation】[Distilling Model Knowledge](https://arxiv.org/pdf/1510.02437.pdf), George Papamakarios, 2015\n- Z. Lin, M. Courbariaux, R. Memisevic, and Y. Bengio. [Neural networks with few multiplications](https://arxiv.org/pdf/1510.03009). arXiv preprint arXiv:1510.03009, 2015. \n- 【Quantization】Courbariaux M, Bengio Y, David J P. [Binaryconnect: Training deep neural networks with binary weights during propagations](https://arxiv.org/pdf/1511.00363.pdf)[C]//Advances in neural information processing systems. 2015: 3123-3131.\n- 【Distillation】[Unifying distillation and privileged information](https://arxiv.org/pdf/1511.03643), David Lopez-Paz, Léon Bottou, Bernhard Schölkopf, Vladimir Vapnik, 2015\n- T. Dettmers. [8-bit approximations for parallelism in deep learning](https://arxiv.org/pdf/1511.04561). arXiv preprint arXiv:1511.04561, 2015. \n- 【Distillation】[Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://arxiv.org/pdf/1511.04508.pdf), Nicolas Papernot, Patrick McDaniel, Xi Wu, Somesh Jha, Ananthram Swami, 2015\n- 【Distillation】[Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization](https://arxiv.org/pdf/1511.04798), Baohan Xu, Yanwei Fu, Yu-Gang Jiang, Boyang Li, Leonid Sigal, 2015\n- 【other】Judd P, Albericio J, Hetherington T, et al. [Reduced-precision strategies for bounded memory in deep neural nets](https://arxiv.org/pdf/1511.05236)[J]. arXiv preprint arXiv:1511.05236, 2015.\n- 【Distillation】Tianqi Chen, Ian Goodfellow, Jonathon Shlens .[Net2Net: Accelerating Learning via Knowledge Transfer](https://arxiv.org/pdf/1511.05641) .[J] arXiv preprint arXiv:1511.05641\n- 【Low Rank】Cheng Tai, Tong Xiao, Yi Zhang, Xiaogang Wang, Weinan E .[Convolutional neural networks with low-rank regularization](https://arxiv.org/pdf/1511.06067) .[J] arXiv preprint arXiv:1511.06067\n- 【Low Rank】Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, Dongjun Shin .[Compression of Deep Convolutional Neural Networks for Fast and Low Power  Mobile Applications](https://arxiv.org/pdf/1511.06530) .[J] arXiv preprint arXiv:1511.06530\n- 【System】Seyyed Salar Latifi Oskouei, Hossein Golestani, Matin Hashemi, Soheil Ghiasi .[CNNdroid: GPU-Accelerated Execution of Trained Deep Convolutional Neural  Networks on Android](https://arxiv.org/pdf/1511.07376) .[J] arXiv preprint arXiv:1511.07376\n- 【Structure】mjad Almahairi, Nicolas Ballas, Tim Cooijmans, Yin Zheng, Hugo Larochelle, Aaron Courville .[Dynamic Capacity Networks](https://arxiv.org/pdf/1511.07838) .[J] arXiv preprint arXiv:1511.07838\n- 【Quantization】Sungho Shin, Kyuyeon Hwang, Wonyong Sung .[Fixed-Point Performance Analysis of Recurrent Neural Networks](https://arxiv.org/pdf/1512.01322) .[J] arXiv preprint arXiv:1512.01322\n- 【Quantization】Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, Jian Cheng .[Quantized Convolutional Neural Networks for Mobile Devices](https://arxiv.org/pdf/1512.06473) .[J] arXiv preprint arXiv:1512.06473\u003cbr\u003e【code:[jiaxiang-wu/quantized-cnn](https://github.com/jiaxiang-wu/quantized-cnn)】\n- 【Distillation】[Learning Using Privileged Information: Similarity Control and Knowledge Transfer](http://www.jmlr.org/papers/volume16/vapnik15b/vapnik15b.pdf), Vladimir Vapnik, Rauf Izmailov, 2015\n\n\n### 2016\n- 【other】Li D, Wang X, Kong D, et al. [DeepRebirth: A General Approach for Accelerating Deep Neural Network Execution on Mobile Devices](https://openreview.net/pdf?id=SkwSJ99ex)[J]. 2016.\n- Luo P, Zhu Z, Liu Z, et al. [Face model compression by distilling knowledge from neurons](https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11977/12130)[C]//Thirtieth AAAI Conference on Artificial Intelligence. 2016.\n- 【Distillation】Lavin A, Gray S. [Fast algorithms for convolutional neural networks](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Lavin_Fast_Algorithms_for_CVPR_2016_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016: 4013-4021.\n- 【Distillation】Luo, Ping, et al. [MobileID: Face Model Compression by Distilling Knowledge from Neurons](https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/11977) Thirtieth AAAI Conference on Artificial Intelligence. 2016.\n- Y.Wang, J. Xu, Y. Han, H. Li, and X. Li. [Deepburning: automatic generation of fpga-based learning accelerators for the neural network family](http://papers.nips.cc/paper/5647-binaryconnect-training-deep-neural-networks-with-binary-weights-during-propagations.pdf). In Design Automation Conference, page 110, 2016. \n- Y. Guo, A. Yao, and Y. Chen. [Dynamic network surgery for efficient dnns](http://papers.nips.cc/paper/6165-dynamic-network-surgery-for-efficient-dnns.pdf). In Advances In Neural Information Processing Systems, pages 1379–1387, 2016. \n- W. Wen, C. Wu, Y. Wang, Y. Chen, and H. Li. [Learning structured sparsity in deep neural networks.](https://papers.nips.cc/paper/6504-learning-structured-sparsity-in-deep-neural-networks.pdf) In Advances in Neural Information Processing Systems, pages 2074–2082, 2016.\n- 【Pruning】V. Lebedev and V. Lempitsky. [Fast convnets using groupwise brain damage](http://openaccess.thecvf.com/content_cvpr_2016/papers/Lebedev_Fast_ConvNets_Using_CVPR_2016_paper.pdf). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2554– 2564, 2016. \n- 【Pruning】Molchanov, Pavlo, et al. [Pruning convolutional neural networks for resource efficient transfer learning](https://pdfs.semanticscholar.org/026e/cf916023e13191331a354271b7f9b86e50a1.pdf). arXiv preprint arXiv:1611.06440 3 (2016). \n- 【Pruning】 Sun Y, Wang X, Tang X. [Sparsifying neural network connections for face recognition](http://openaccess.thecvf.com/content_cvpr_2016/papers/Sun_Sparsifying_Neural_Network_CVPR_2016_paper.pdf) .[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016: 4856-4864.\n- 【Pruning】Babaeizadeh, Mohammad, Paris Smaragdis, and Roy H. Campbell. [A Simple yet Effective Method to Prune Dense Layers of Neural Networks](https://openreview.net/forum?id=HJIY0E9ge\u0026noteId=HJIY0E9ge) (2016).\n- S. Zhang, Z. Du, L. Zhang, H. Lan, S. Liu, L. Li, Q. Guo, T. Chen, and Y. Chen. [Cambricon-x: An accelerator for sparse neural networks](http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f1/Cambricon-X.pdf). In Ieee/acm International Symposium on Microarchitecture, pages 1–12, 2016.\n- S. I. Venieris and C. S. Bouganis. [fpgaconvnet: A framework for mapping convolutional neural networks on fpgas](https://spiral.imperial.ac.uk/bitstream/10044/1/44130/2/FCCM2016_camera_ready.pdf). In IEEE International Symposium on Field-Programmable Custom Computing Machines, pages 40–47, 2016.\n- S. Liu, Z. Du, J. Tao, D. Han, T. Luo, Y. Xie, Y. Chen, and T. Chen. [Cambricon: An instruction set architecture for neural networks]. SIGARCH Comput. Archit. News, 44(3), June 2016.\n- Suda. [Throughput-optimized opencl-based fpga accelerator for large-scale convolutional neural networks](http://isfpga.org/fpga2016/index_files/Slides/1_1.pdf). In Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA ’16, 2016.\n- P. Wang and J. Cheng. [Accelerating convolutional neural networks for mobile applications](http://ir.ia.ac.cn/bitstream/173211/20148/1/Accelerating%20Convolutional%20Neural%20Networks%20for%20Mobile%20Applications.pdf). In Proceedings of the 2016 ACM on Multimedia Conference, pages 541–545. ACM, 2016.\n- Qiu. [Going deeper with embedded fpga platform for convolutional neural network.](http://www.isfpga.org/fpga2016/index_files/Slides/1_2.pdf) In Proceedings of the 2016 ACM/SIGDA International Symposium on Field- Programmable Gate Arrays, FPGA ’16, 2016. \n- L. Xia, T. Tang, W. Huangfu, M. Cheng, X. Yin, B. Li, Y. Wang, and H. Yang. [Switched by input: Power efficient structure for rram-based convolutional neural network](http://nicsefc.ee.tsinghua.edu.cn/media/publications/2016/DAC16_197.pdf). In Design Automation Conference, page 125, 2016.\n- M. Alwani, H. Chen, M. Ferdman, and P. A. Milder. [Fusedlayer cnn accelerators](https://pdfs.semanticscholar.org/f30c/0a35edeaa8799a30851a74b974d293f9f3bf.pdf). In MICRO, 2016.\n- K. Kim, J. Kim, J. Yu, J. Seo, J. Lee, and K. Choi. [Dynamic energy-accuracy trade-off using stochastic computing in deep neural networks]. In Design Automation Conference, page 124, 2016.\n- J. Zhu, Z. Qian, and C. Y. Tsui. [Lradnn: High-throughput and energy-efficient deep neural network accelerator using low rank approximation](http://www.aspdac.com/aspdac2016/technical_program/pdf/6B-4.pdf). In Asia and South Pacific Design Automation Conference, pages 581–586, 2016.\n- J. Wu, C. Leng, Y. Wang, Q. Hu, and J. Cheng.[Quantized convolutional neural networks for mobile devices](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Wu_Quantized_Convolutional_Neural_CVPR_2016_paper.pdf). IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.\n- J. Albericio, P. Judd, T. Hetherington, T. Aamodt, N. E. Jerger, and A. Moshovos. [Cnvlutin: Ineffectual-neuron-free deep neural network computing](https://www.ece.ubc.ca/~aamodt/publications/papers/Cnvlutin.ISCA2016.pdf). In International Symposium on Computer Architecture, pages 1–13, 2016. \n- H. Sharma, J. Park, D. Mahajan, E. Amaro, J. K. Kim, C. Shao, A. Mishra, and H. Esmaeilzadeh. [From highlevel deep neural models to fpgas.](https://www.cc.gatech.edu/~hesmaeil/doc/paper/2016-micro-dnn_weaver.pdf) In Ieee/acm International Symposium on Microarchitecture, pages 1–12, 2016. \n- D. Kim, J. Kung, S. Chai, S. Yalamanchili, and S. Mukhopadhyay. [Neurocube: A programmable digital neuromorphic architecture with high-density 3d memory](http://isca2016.eecs.umich.edu/wp-content/uploads/2016/07/6-2.pdf). In International Symposium on Computer Architecture, pages 380–392, 2016.\n- C. Zhang, D. Wu, J. Sun, G. Sun, G. Luo, and J. Cong.[Energy-efficient cnn implementation on a deeply pipelined fpga cluster](http://vast.cs.ucla.edu/sites/default/files/publications/islped_chen.pdf). In Proceedings of the 2016 International Symposium on Low Power Electronics and Design, ISLPED ’16, 2016.\n- C. Zhang, Z. Fang, P. Pan, P. Pan, and J. Cong. [Caffeine: towards uniformed representation and acceleration for deep convolutional neural networks](https://iceory.github.io/2018/04/25/caffeine-slides/Caffeine.pdf). In International Conference on Computer-Aided Design, page 12, 2016.\n- 【Quantization】 Lin, Darryl, Sachin Talathi, and Sreekanth Annapureddy. [Fixed point quantization of deep convolutional networks.](http://www.jmlr.org/proceedings/papers/v48/linb16.pdf) International Conference on Machine Learning. 2016.\n- 【Binarization】Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio .[Binarized Neural Networks: Training Deep Neural Networks with Weights  and Activations Constrained to +1 or -1](https://arxiv.org/pdf/1602.02830) .[J] arXiv preprint arXiv:1602.02830\u003cbr\u003e【code:[itayhubara/BinaryNet.pytorch](https://github.com/itayhubara/BinaryNet.pytorch); [itayhubara/BinaryNet.tf](https://github.com/itayhubara/BinaryNet.tf)】\n- 【Binarization】Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi .[XNOR-Net: ImageNet Classification Using Binary Convolutional Neural  Networks](https://arxiv.org/pdf/1603.05279) .[J] arXiv preprint arXiv:1603.05279\u003cbr\u003e【code:[allenai/XNOR-Net](https://github.com/allenai/XNOR-Net)】\n- 【System】Huynh, Loc Nguyen, Rajesh Krishna Balan, and Youngki Lee. [DeepSense: A GPU-based deep convolutional neural network framework on commodity mobile devices](http://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=4278\u0026context=sis_research) Proceedings of the 2016 Workshop on Wearable Systems and Applications. ACM, 2016.\n- 【System】Lane, Nicholas D., et al. [DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices](http://niclane.org/pubs/deepx_ipsn.pdf) .[C]Proceedings of the 15th International Conference on Information Processing in Sensor Networks. IEEE Press, 2016.\n- 【System】Lane, Nicholas D., et al. [DXTK: Enabling Resource-efficient Deep Learning on Mobile and Embedded Devices with the DeepX Toolkit](http://niclane.org/pubs/dxtk_mobicase.pdf)  .[J]MobiCASE. 2016.\n- 【System】Han, Seungyeop, et al. [MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints](http://haneul.github.io/papers/mcdnn.pdf) .[C]Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services. ACM, 2016.\n- 【System】Bhattacharya, Sourav, and Nicholas D. Lane. [Sparsification and Separation of Deep Learning Layers for Constrained Resource Inference on Wearables](http://niclane.org/pubs/sparsesep_sensys.pdf) .[C]Proceedings of the 14th ACM Conference on Embedded Network Sensor Systems CD-ROM. ACM, 2016.\n- M. Kim and P. Smaragdis. [Bitwise neural networks](https://arxiv.org/pdf/1601.06071). arXiv preprint arXiv:1601.06071, 2016. \n- 【System】Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark A. Horowitz, William J. Dally .[EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://arxiv.org/pdf/1602.01528) .[J] arXiv preprint arXiv:1602.01528\n- 【Structure】【SqueezeNet】Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer .[SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \u003c0.5MB  model size](https://arxiv.org/pdf/1602.07360) .[J] arXiv preprint arXiv:1602.07360\n- D. Miyashita, E. H. Lee, and B. Murmann. [Convolutional neural networks using logarithmic data representation](https://arxiv.org/pdf/1603.01025). arXiv preprint arXiv:1603.01025, 2016. \n- 【Distillation】[Do deep convolutional nets really need to be deep and convolutional?](https://arxiv.org/pdf/1603.05691.pdf), Gregor Urban, Krzysztof J. Geras, Samira Ebrahimi Kahou, Ozlem Aslan, Shengjie Wang, Rich Caruana, Abdelrahman Mohamed, Matthai Philipose, Matt Richardson, 2016\n- 【Structure】Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, Kilian Weinberger .[Deep Networks with Stochastic Depth](https://arxiv.org/pdf/1603.09382) .[J] arXiv preprint arXiv:1603.09382\n- 【Distillation】[Adapting Models to Signal Degradation using Distillation](https://arxiv.org/abs/1604.00433), Jong-Chyi Su, Subhransu Maji,2016\n- F. Li, B. Zhang, and B. Liu. [Ternary weight networks](https://arxiv.org/pdf/1605.04711) . arXiv preprint arXiv:1605.04711, 2016. \u003cbr\u003e【code:[fengfu-chris/caffe-twns](https://github.com/fengfu-chris/caffe-twns)】\n- 【Quantization】 Gysel, Philipp. [Ristretto: Hardware-oriented approximation of convolutional neural networks.](https://arxiv.org/pdf/1604.03168.pdf) arXiv preprint arXiv:1605.06402 (2016).\n- 【Structure】Roi Livni, Daniel Carmon, Amir Globerson .[Learning Infinite-Layer Networks: Without the Kernel Trick](https://arxiv.org/pdf/1606.05316) .[J] arXiv preprint arXiv:1606.05316\n- 【Quantization】Zen H, Agiomyrgiannakis Y, Egberts N, et al. [Fast, compact, and high quality LSTM-RNN based statistical parametric speech synthesizers for mobile devices](https://arxiv.org/pdf/1606.06061)[J]. arXiv preprint arXiv:1606.06061, 2016.\n- 【Binarization】Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, Yuheng Zou .[DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low  Bitwidth Gradients](https://arxiv.org/pdf/1606.06160) .[J] arXiv preprint arXiv:1606.06160\u003cbr\u003e【code:[tensorpack/DoReFa-Net](https://github.com/tensorpack/tensorpack/tree/master/examples/DoReFa-Net)】\n- 【Distillation】Yoon Kim, Alexander M. Rush .[Sequence-Level Knowledge Distillation](https://arxiv.org/pdf/1606.07947) .[J] arXiv preprint arXiv:1606.07947\n- 【Structure】【Pruning】Song Han, Jeff Pool, Sharan Narang, Huizi Mao, Enhao Gong, Shijian Tang, Erich Elsen, Peter Vajda, Manohar Paluri, John Tran, Bryan Catanzaro, William J. Dally .[DSD: Dense-Sparse-Dense Training for Deep Neural Networks](https://arxiv.org/pdf/1607.04381) .[J] arXiv preprint arXiv:1607.04381\u003cbr\u003e【code:[songhan.github.io/DSD](https://songhan.github.io/DSD)】\n- 【Quantization】Alvarez R, Prabhavalkar R, Bakhtin A. [On the efficient representation and execution of deep acoustic models](https://arxiv.org/pdf/1607.04683)[J]. arXiv preprint arXiv:1607.04683, 2016.\n- 【Distillation】[Knowledge Distillation for Small-footprint Highway Networks](https://arxiv.org/pdf/1608.00892), Liang Lu, Michelle Guo, Steve Renals, 2016\n- 【Pruning】Jongsoo Park, Sheng Li, Wei Wen, Ping Tak Peter Tang, Hai Li, Yiran Chen, Pradeep Dubey .[Faster CNNs with Direct Sparse Convolutions and Guided Pruning](https://arxiv.org/pdf/1608.01409) .[J] arXiv preprint arXiv:1608.01409\u003cbr\u003e【code:[IntelLabs/SkimCaffe](https://github.com/IntelLabs/SkimCaffe)】\n- 【Pruning】Wei Wen, Chunpeng Wu, Yandan Wang, Yiran Chen, Hai Li .[Learning Structured Sparsity in Deep Neural Networks](https://arxiv.org/pdf/1608.03665) .[J] arXiv preprint arXiv:1608.03665\u003cbr\u003e【code:[wenwei202/caffe/tree/scnn](https://github.com/wenwei202/caffe/tree/scnn)】\n- 【Structure】 Wang M, Liu B, Foroosh H. [Design of efficient convolutional layers using single intra-channel convolution, topological subdivisioning and spatial\" bottleneck\" structure](https://arxiv.org/pdf/1608.04337) .[J]. arXiv preprint arXiv:1608.04337, 2016.\n- 【Pruning】Yiwen Guo, Anbang Yao, Yurong Chen .[Dynamic Network Surgery for Efficient DNNs](https://arxiv.org/pdf/1608.04493) .[J] arXiv preprint arXiv:1608.04493\u003cbr\u003e【code:[yiwenguo/Dynamic-Network-Surgery](https://github.com/yiwenguo/Dynamic-Network-Surgery)】\n- 【Binarization】Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides .[Local Binary Convolutional Neural Networks](https://arxiv.org/pdf/1608.06049) .[J] arXiv preprint arXiv:1608.06049\n- 【Pruning】Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, Hans Peter Graf .[Pruning Filters for Efficient ConvNets](https://arxiv.org/pdf/1608.08710) .[J] arXiv preprint arXiv:1608.08710\u003cbr\u003e【code:[Eric-mingjie/rethinking-network-pruning](https://github.com/Eric-mingjie/rethinking-network-pruning/tree/master/imagenet/l1-norm-pruning)】\n- 【other】Tramèr F, Zhang F, Juels A, et al. [Stealing machine learning models via prediction apis](https://arxiv.org/pdf/1609.02943.pdf)[C]//25th {USENIX} Security Symposium ({USENIX} Security 16). 2016: 601-618.\n- 【Quantization】Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio .[Quantized Neural Networks: Training Neural Networks with Low Precision  Weights and Activations](https://arxiv.org/pdf/1609.07061) .[J] arXiv preprint arXiv:1609.07061\n- 【Quantization】Wu Y, Schuster M, Chen Z, et al. [Google's neural machine translation system: Bridging the gap between human and machine translation](https://arxiv.org/abs/1609.08144)[J]. arXiv preprint arXiv:1609.08144, 2016.\n- 【Structure】【Xception】François Chollet .[Xception: Deep Learning with Depthwise Separable Convolutions](https://arxiv.org/pdf/1610.02357) .[J] arXiv preprint arXiv:1610.02357\n- 【Distillation】Bharat Bhusan Sau, Vineeth N. Balasubramanian .[Deep Model Compression: Distilling Knowledge from Noisy Teachers](https://arxiv.org/pdf/1610.09650) .[J] arXiv preprint arXiv:1610.09650\n- 【other】Li X, Qin T, Yang J, et al. [LightRNN: Memory and computation-efficient recurrent neural networks](https://arxiv.org/abs/1610.09893)[C]//Advances in Neural Information Processing Systems. 2016: 4385-4393.\n- 【Quantization】Lu Hou, Quanming Yao, James T. Kwok .[Loss-aware Binarization of Deep Networks](https://arxiv.org/pdf/1611.01600) .[J] arXiv preprint arXiv:1611.01600\n- 【Low rank】Garipov T, Podoprikhin D, Novikov A, et al. [Ultimate tensorization: compressing convolutional and fc layers alike](https://arxiv.org/pdf/1611.03214)[J]. arXiv preprint arXiv:1611.03214, 2016.\u003cbr\u003e【code:[timgaripov/TensorNet-TF](https://github.com/timgaripov/TensorNet-TF);[Bihaqo/TensorNet](https://github.com/Bihaqo/TensorNet)】\n- 【Pruning】Tien-Ju Yang, Yu-Hsin Chen, Vivienne Sze .[Designing Energy-Efficient Convolutional Neural Networks using  Energy-Aware Pruning](https://arxiv.org/pdf/1611.05128) .[J] arXiv preprint arXiv:1611.05128\n- 【Pruning】Aghasi A, Abdi A, Nguyen N, et al. [Net-trim: Convex pruning of deep neural networks with performance guarantee](https://arxiv.org/abs/1611.05162)[C]//Advances in Neural Information Processing Systems. 2017: 3177-3186.\u003cbr\u003e【code:[DNNToolBox/Net-Trim-v1](https://github.com/DNNToolBox/Net-Trim-v1)】\n- 【Quantization】Hantian Zhang, Jerry Li, Kaan Kara, Dan Alistarh, Ji Liu, Ce Zhang .[The ZipML Framework for Training Models with End-to-End Low Precision:  The Cans, the Cannots, and a Little Bit of Deep Learning](https://arxiv.org/pdf/1611.05402) .[J] arXiv preprint arXiv:1611.05402\n- 【Structure】Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He .[Aggregated Residual Transformations for Deep Neural Networks](https://arxiv.org/pdf/1611.05431) .[J] arXiv preprint arXiv:1611.05431\n- A. Ren, Z. Li, C. Ding, Q. Qiu, Y. Wang, J. Li, X. Qian, and B. Yuan. [Sc-dcnn: Highly-scalable deep convolutional neural network using stochastic computing](https://arxiv.org/pdf/1611.05939). arXiv preprint arXiv:1611.05939, 2016.  \n- 【Pruning】Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, Jan Kautz .[Pruning Convolutional Neural Networks for Resource Efficient Inference](https://arxiv.org/pdf/1611.06440) .[J] arXiv preprint arXiv:1611.06440\u003cbr\u003e【code:[Tencent/PocketFlow#channel-pruning](https://github.com/Tencent/PocketFlow#channel-pruning)】\n- 【other】Bagherinezhad H, Rastegari M, Farhadi A. [Lcnn: Lookup-based convolutional neural network](https://arxiv.org/pdf/1611.06473.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 7120-7129.\n- 【Quantization】Hong S, Roh B, Kim K H, et al. [Pvanet: Lightweight deep neural networks for real-time object detection](https://arxiv.org/abs/1611.08588)[J]. arXiv preprint arXiv:1611.08588, 2016.\u003cbr\u003e【code:[sanghoon/pva-faster-rcnn](https://github.com/sanghoon/pva-faster-rcnn)】\n- 【Quantization】Qinyao He, He Wen, Shuchang Zhou, Yuxin Wu, Cong Yao, Xinyu Zhou, Yuheng Zou .[Effective Quantization Methods for Recurrent Neural Networks](https://arxiv.org/pdf/1611.10176) .[J] arXiv preprint arXiv:1611.10176\n- 【Distallation】 Shen J, Vesdapunt N, Boddeti V N, et al. [In teacher we trust: Learning compressed models for pedestrian detection](https://arxiv.org/pdf/1612.00478.pdf) .[J]. arXiv preprint arXiv:1612.00478, 2016.\n- 【Pruning】Song Han, Junlong Kang, Huizi Mao, Yiming Hu, Xin Li, Yubin Li, Dongliang Xie, Hong Luo, Song Yao, Yu Wang, Huazhong Yang, William J. Dally .[ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA](https://arxiv.org/pdf/1612.00694) .[J] arXiv preprint arXiv:1612.00694\n- 【Structure】Bichen Wu, Alvin Wan, Forrest Iandola, Peter H. Jin, Kurt Keutzer .[SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural  Networks for Real-Time Object Detection for Autonomous Driving](https://arxiv.org/pdf/1612.01051) .[J] arXiv preprint arXiv:1612.01051\n- 【Quantization】Zhu C, Han S, Mao H, et al. [Trained ternary quantization](https://arxiv.org/pdf/1612.01064)[J]. arXiv preprint arXiv:1612.01064, 2016.\u003cbr\u003e【code:[czhu95/ternarynet](https://github.com/czhu95/ternarynet)】\n- 【Quantization】Yoojin Choi, Mostafa El-Khamy, Jungwon Lee .[Towards the Limit of Network Quantization](https://arxiv.org/pdf/1612.01543) .[J] arXiv preprint arXiv:1612.01543\n- 【other】Joulin A, Grave E, Bojanowski P, et al. [Fasttext. zip: Compressing text classification models](https://arxiv.org/pdf/1612.03651)[J]. arXiv preprint arXiv:1612.03651, 2016.\n- 【Distillation】Sergey Zagoruyko, Nikos Komodakis .[Paying More Attention to Attention: Improving the Performance of  Convolutional Neural Networks via Attention Transfer](https://arxiv.org/pdf/1612.03928) .[J] arXiv preprint arXiv:1612.03928\n- 【other】Hashemi S, Anthony N, Tann H, et al. [Understanding the impact of precision quantization on the accuracy and energy of neural networks](https://arxiv.org/pdf/1612.03940)[C]//Design, Automation \u0026 Test in Europe Conference \u0026 Exhibition (DATE), 2017. IEEE, 2017: 1474-1479.\n- Umuroglu. [Finn: A framework for fast, scalable binarized neural network inference](https://arxiv.org/pdf/1612.07119).[J] arXiv preprint arXiv:1612.07119\n\n\n### 2017\n- 【Thesis】Han S, Dally B. [Efficient methods and hardware for deep learning](https://stacks.stanford.edu/file/druid:qf934gh3708/EFFICIENT%20METHODS%20AND%20HARDWARE%20FOR%20DEEP%20LEARNING-augmented.pdf)[J]. University Lecture, 2017.\n- 【Quantization】Cai Z, He X, Sun J, et al. [Deep learning with low precision by half-wave gaussian quantization](http://openaccess.thecvf.com/content_cvpr_2017/papers/Cai_Deep_Learning_With_CVPR_2017_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 5918-5926.\u003cbr\u003e【code:[zhaoweicai/hwgq](https://github.com/zhaoweicai/hwgq)】\n- 【Quantization】Yonekawa H, Nakahara H. [On-chip memory based binarized convolutional deep neural network applying batch normalization free technique on an fpga](https://www.researchgate.net/profile/Hiroki_Nakahara/publication/318127383_On-Chip_Memory_Based_Binarized_Convolutional_Deep_Neural_Network_Applying_Batch_Normalization_Free_Technique_on_an_FPGA/links/5b59efffaca272a2d66cb247/On-Chip-Memory-Based-Binarized-Convolutional-Deep-Neural-Network-Applying-Batch-Normalization-Free-Technique-on-an-FPGA.pdf)[C]//2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 2017: 98-105.\n- 【Quantization】Liang S, Yin S, Liu L, et al. [FP-BNN: Binarized neural network on FPGA](http://www.doc.ic.ac.uk/~wl/papers/17/neuro17sl0.pdf)[J]. Neurocomputing, 2018, 275: 1072-1086.\n- 【Quantization】Li Z, Ni B, Zhang W, et al. [Performance guaranteed network acceleration via high-order residual quantization](http://openaccess.thecvf.com/content_ICCV_2017/papers/Li_Performance_Guaranteed_Network_ICCV_2017_paper.pdf)[C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 2584-2592.\n- 【Quantization】Hu Q, Wang P, Cheng J. [From hashing to cnns: Training binary weight networks via hashing](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPDFInterstitial/16466/16691)[C]//Thirty-Second AAAI Conference on Artificial Intelligence. 2018.\n- 【Quantization】Lin X, Zhao C, Pan W. [Towards accurate binary convolutional neural network](http://papers.nips.cc/paper/6638-towards-accurate-binary-convolutional-neural-network.pdf)[C]//Advances in Neural Information Processing Systems. 2017: 345-353.\n- 【Binarization】Yang H, Fritzsche M, Bartz C, et al. [Bmxnet: An open-source binary neural network implementation based on mxnet](https://arxiv.org/pdf/1705.09864)[C]//Proceedings of the 25th ACM international conference on Multimedia. ACM, 2017: 1209-1212.\u003cbr\u003e【code:[hpi-xnor/BMXNet](https://github.com/hpi-xnor/BMXNet)】\n- 【Structure】【ResNeXt】S. Xie, R. Girshick, P. Dollar, Z. Tu, and K. He. [ResNeXt: Aggregated residual transformations for deep neural networks](http://openaccess.thecvf.com/content_cvpr_2017/papers/Xie_Aggregated_Residual_Transformations_CVPR_2017_paper.pdf). In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017. \n- 【other】Huang L, Liu X, Liu Y, et al. [Centered weight normalization in accelerating training of deep neural networks](http://openaccess.thecvf.com/content_ICCV_2017/papers/Huang_Centered_Weight_Normalization_ICCV_2017_paper.pdf)[C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 2803-2811.\n- Park E, Ahn J, Yoo S. [Weighted-entropy-based quantization for deep neural networks](http://openaccess.thecvf.com/content_cvpr_2017/papers/Park_Weighted-Entropy-Based_Quantization_for_CVPR_2017_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 5456-5464.\u003cbr\u003e【code:[EunhyeokPark/script_for_WQ](https://github.com/EunhyeokPark/script_for_WQ)】\n- Guo Y, Yao A, Zhao H, et al. Network sketching: Exploiting binary structure in deep cnns](http://openaccess.thecvf.com/content_cvpr_2017/papers/Guo_Network_Sketching_Exploiting_CVPR_2017_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 5955-5963.\n- D. Nguyen, D. Kim, and J. Lee. [Double MAC: doubling the performance of convolutional neural networks on modern fpgas]. In Design, Automation and Test in Europe Conference and Exhibition, DATE 2017, Lausanne, Switzerland, March 27-31, 2017, pages 890–893, 2017. \n- Edward. [Lognet: Energy-efficient neural networks using logarithmic computation]. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5900–5904, 2017. \n- H. Sim and J. Lee. [A new stochastic computing multiplier with application to deep convolutional neural networks]. In Design Automation Conference, page 29, 2017. \n- H. Yang. [Time: A training-in-memory architecture for memristor-based deep neural networks](https://nicsefc.ee.tsinghua.edu.cn/media/publications/2017/DAC17_218.pdf). In Design Automation Conference, page 26, 2017. \n- L. Chen, J. Li, Y. Chen, Q. Deng, J. Shen, X. Liang, and L. Jiang.[ Accelerator-friendly neural-network training: Learning variations and defects in rram crossbar]. In Design, Automation and Test in Europe Conference and Exhibition, pages 19–24, 2017. \n- M. Gao, J. Pu, X. Yang, M. Horowitz, and C. Kozyrakis. [Tetris: Scalable and efficient neural network acceleration with 3d memory](https://dl.acm.org/ft_gateway.cfm?id=3037702\u0026type=pdf). In International Conference on Architectural Support for Programming Languages and Operating Systems, pages 751–764, 2017. \n- M. Price, J. Glass, and A. P. Chandrakasan. [14.4 a scalable speech recognizer with deep-neural-network acoustic models and voice-activated power gating.] In Solid-State Circuits Conference, pages 244–245, 2017. \n- N. P. Jouppi. [In-datacenter performance analysis of a tensor processing unit](https://ieeexplore.ieee.org/iel7/8126322/8192462/08192463.pdf). In Proceedings of the 44th Annual International Symposium on Computer Architecture, ISCA ’17, 2017. \n- Nurvitadhi. [Can fpgas beat gpus in accelerating nextgeneration deep neural networks?](https://jaewoong.org/pubs/fpga17-next-generation-dnns.pdf) In Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA ’17, 2017. \n- P. Wang and J. Cheng. [Fixed-point factorized networks](http://openaccess.thecvf.com/content_cvpr_2017/papers/Wang_Fixed-Point_Factorized_Networks_CVPR_2017_paper.pdf). In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017. \n- S. Venkataramani, A. Ranjan, S. Banerjee, D. Das, S. Avancha, A. Jagannathan, A. Durg, D. Nagaraj, B. Kaul, P. Dubey, and A. Raghunathan. [Scaledeep: A scalable compute architecture for learning and evaluating deep networks]. SIGARCH Comput. Archit. News, 45(2):13–26, June 2017. \n- Wei. [Automated systolic array architecture synthesis for high throughput cnn inference on fpgas](http://ceca.pku.edu.cn/media/lw/6c22198b68248a761d8d8469080b48f1.pdf). In Proceedings of the 54th Annual Design Automation Conference 2017, DAC ’17, 2017. \n- W. Tang, G. Hua, and L. Wang. [How to train a compact binary neural network with high accuracy?](https://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/download/14619/14454) In AAAI, pages 2625–2631, 2017. \n- Xiao. [Exploring heterogeneous algorithms for accelerating deep convolutional neural networks on fpgas](http://ceca.pku.edu.cn/media/lw/9b2b54e7fbe742e085ca6c1ae1502791.pdf). In Proceedings of the 54th Annual Design Automation Conference 2017, DAC ’17, 2017. \n- Y. H. Chen, T. Krishna, J. S. Emer, and V. Sze. [Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks](https://dspace.mit.edu/openaccess-disseminate/1721.1/101151). IEEE Journal of Solid-State Circuits, 52(1):127–138, 2017. \n- Y. Ma, M. Kim, Y. Cao, S. Vrudhula, J. S. Seo, Y. Ma, M. Kim, Y. Cao, S. Vrudhula, and J. S. Seo. [End-to-end scalable fpga accelerator for deep residual networks.] In IEEE International Symposium on Circuits and Systems, pages 1–4, 2017. \n- Y. Ma, Y. Cao, S. Vrudhula, and J. S. Seo. [An automatic rtl compiler for high-throughput fpga implementation of diverse deep convolutional neural networks]. In International Conference on Field Programmable Logic and Applications, pages 1–8, 2017. \n- Y. Ma, Y. Cao, S. Vrudhula, and J.-s. Seo. [Optimizing loop operation and dataflow in fpga acceleration of deep convolutional neural networks](http://www.isfpga.org/fpga2017/slides/D1_S1_04.pdf). In Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA ’17, 2017. \n- Y. Shen, M. Ferdman, and P. Milder. [Escher: A cnn accelerator with flexible buffering to minimize off-chip transfer](https://www.computer.org/csdl/proceedings/fccm/2017/4037/00/07966659.pdf). In IEEE International Symposium on Field-Programmable Custom Computing Machines, 2017. \n- Zhao. [Accelerating binarized convolutional neural networks with software-programmable fpgas](https://dl.acm.org/ft_gateway.cfm?id=3021741\u0026type=pdf). In Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA ’17, 2017. \n- 【Distillation】Yim J, Joo D, Bae J, et al. [A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learnin](https://pdfs.semanticscholar.org/0410/659b6a311b281d10e0e44abce9b1c06be462.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 4133-4141.\n- 【Distillation】Chen G, Choi W, Yu X, et al. [Learning Efficient Object Detection Models with Knowledge Distillation](http://papers.nips.cc/paper/6676-learning-efficient-object-detection-models-with-knowledge-distillation.pdf)[C]//Advances in Neural Information Processing Systems. 2017: 742-751.\n- 【Distillation】[Local Affine Approximators for Improving Knowledge Transfer](https://lld-workshop.github.io/papers/LLD_2017_paper_28.pdf), Suraj Srinivas and Francois Fleuret, 2017\n- 【Distillation】[Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model](http://papers.nips.cc/paper/6635-best-of-both-worlds-transferring-knowledge-from-discriminative-learning-to-a-generative-visual-dialog-model.pdf), Jiasen Lu1, Anitha Kannan, Jianwei Yang, Devi Parikh, Dhruv Batra 2017\n- 【Distillation】[Data-Free Knowledge Distillation For Deep Neural Networks](http://raphagl.com/research/replayed-distillation/), Raphael Gontijo Lopes, Stefano Fenu, 2017 \n- 【Miscellaneous】Wang Y, Xu C, Xu C, et al. [Beyond Filters: Compact Feature Map for Portable Deep Model](http://proceedings.mlr.press/v70/wang17m/wang17m.pdf)[C]//Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 2017: 3703-3711.\n- 【Miscellaneous】Kim J, Park Y, Kim G, et al. [SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization](http://proceedings.mlr.press/v70/kim17b/kim17b.pdf)[C]//Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 2017: 1866-1874.\n- 【Pruning】He Y, Zhang X, Sun J. [Channel pruning for accelerating very deep neural networks](http://openaccess.thecvf.com/content_ICCV_2017/papers/He_Channel_Pruning_for_ICCV_2017_paper.pdf)[C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 1389-1397.\n- 【Pruning】J. H. Ko, B. Mudassar, T. Na, and S. Mukhopadhyay. [Design of an energy-efficient accelerator for training of convolutional neural networks using frequency-domain computation](https://papers.nips.cc/paper/7382-frequency-domain-dynamic-pruning-for-convolutional-neural-networks.pdf). In Design Automation Conference, page 59, 2017. \n- 【Pruning】Neklyudov K, Molchanov D, Ashukha A, et al. [Structured bayesian pruning via log-normal multiplicative noise](https://papers.nips.cc/paper/7254-structured-bayesian-pruning-via-log-normal-multiplicative-noise.pdf)[C]//Advances in Neural Information Processing Systems. 2017: 6775-6784.\u003cbr\u003e【code;[necludov/group-sparsity-sbp](https://github.com/necludov/group-sparsity-sbp)】\n- 【Pruning】Mallya A, Lazebnik S. [Packnet: Adding multiple tasks to a single network by iterative pruning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Mallya_PackNet_Adding_Multiple_CVPR_2018_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 7765-7773.\u003cbr\u003e【code:[arunmallya/packnet](https://github.com/arunmallya/packnet)】\n- 【Pruning】Vieira T, Eisner J. [Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing](http://www.cs.jhu.edu/~jason/papers/vieira+eisner.tacl17.pdf)[J]. Transactions of the Association for Computational Linguistics, 2017, 5: 263-278.\n- 【Pruning】Yu J, Lukefahr A, Palframan D, et al. [Scalpel: Customizing DNN Pruning to the Underlying Hardware Parallelism](http://www-personal.umich.edu/~jiecaoyu/papers/jiecaoyu-isca17.pdf)[C]//ACM SIGARCH Computer Architecture News. ACM, 2017, 45(2): 548-560.\n- 【Pruning】Lin J, Rao Y, Lu J, et al. [Runtime neural pruning](http://papers.nips.cc/paper/6813-runtime-neural-pruning)[C]//Advances in Neural Information Processing Systems. 2017: 2181-2191.\n- 【System】Mathur A, Lane N D, Bhattacharya S, et al.[DeepEye: Resource Efficient Local Execution of Multiple Deep Vision Models using Wearable Commodity Hardware](http://fahim-kawsar.net/papers/Mathur.MobiSys2017-Camera.pdf)[C]//Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services. ACM, 2017: 68-81.\n- 【System】Huynh L N, Lee Y, Balan R K. [DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications](http://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=4673\u0026context=sis_research)[C]//Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services. ACM, 2017: 82-95.\n- Anwar S, Hwang K, Sung W. [Structured pruning of deep convolutional neural networks.](https://dl.acm.org/citation.cfm?id=3005348)[J]. ACM Journal on Emerging Technologies in Computing Systems (JETC), 2017, 13(3): 32.\n- He Y, Zhang X, Sun J. [Channel pruning for accelerating very deep neural networks](http://openaccess.thecvf.com/content_ICCV_2017/papers/He_Channel_Pruning_for_ICCV_2017_paper.pdf)[C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 1389-1397.\n- Aghasi A, Abdi A, Nguyen N, et al. [Net-trim: Convex pruning of deep neural networks with performance guarantee.](http://papers.nips.cc/paper/6910-net-trim-convex-pruning-of-deep-neural-networks-with-performance-guarantee)[C]//Advances in Neural Information Processing Systems. 2017: 3177-3186.\n- 【Quantization】Meng W, Gu Z, Zhang M, et al. [Two-bit networks for deep learning on resource-constrained embedded devices](https://arxiv.org/pdf/1701.00485)[J]. arXiv preprint arXiv:1701.00485, 2017.\n- 【other】Ghosh T. [Quicknet: Maximizing efficiency and efficacy in deep architectures](https://arxiv.org/pdf/1701.02291)[J]. arXiv preprint arXiv:1701.02291, 2017.\n- 【Pruning】Wolfe N, Sharma A, Drude L, et al. [The incredible shrinking neural network: New perspectives on learning representations through the lens of pruning](https://arxiv.org/abs/1701.04465)[J]. 2016.\n- 【other】Chandrasekhar V, Lin J, Liao Q, et al. [Compression of deep neural networks for image instance retrieval](https://arxiv.org/pdf/1701.04923)[C]//2017 Data Compression Conference (DCC). IEEE, 2017: 300-309.\n- 【other】Molchanov D, Ashukha A, Vetrov D. [Variational dropout sparsifies deep neural networks](https://arxiv.org/pdf/1701.05369)[C]//Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 2017: 2498-2507.\u003cbr\u003e【code:[ars-ashuha/variational-dropout-sparsifies-dnn](https://github.com/ars-ashuha/variational-dropout-sparsifies-dnn)】\n- 【Decomposition】Astrid M, Lee S I. [Cp-decomposition with tensor power method for convolutional neural networks compression](https://arxiv.org/pdf/1701.07148)[C]//2017 IEEE International Conference on Big Data and Smart Computing (BigComp). IEEE, 2017: 115-118.\n- 【Quantization】Zhaowei Cai, Xiaodong He, Jian Sun, Nuno Vasconcelos .[Deep Learning with Low Precision by Half-wave Gaussian Quantization](https://arxiv.org/pdf/1702.00953) .[J] arXiv preprint arXiv:1702.00953\n- 【Quantization】 Zhou, Aojun, et al. [Incremental network quantization: Towards lossless cnns with low-precision weights.](https://arxiv.org/pdf/1702.03044.pdf) arXiv preprint arXiv:1702.03044 (2017).\n- 【Pruning】Karen Ullrich, Edward Meeds, Max Welling .[Soft Weight-Sharing for Neural Network Compression](https://arxiv.org/pdf/1702.04008) .[J] arXiv preprint arXiv:1702.04008\n- 【Pruning】Changpinyo S, Sandler M, Zhmoginov A. [The power of sparsity in convolutional neural networks](https://arxiv.org/pdf/1702.06257)[J]. arXiv preprint arXiv:1702.06257, 2017.\n- 【Quantization】Shin S, Boo Y, Sung W. [Fixed-point optimization of deep neural networks with adaptive step size retraining](https://arxiv.org/pdf/1702.08171)[C]//2017 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE, 2017: 1203-1207.\n- 【Quantization】Graham B. [Low-precision batch-normalized activations](https://arxiv.org/pdf/1702.08231)[J]. arXiv preprint arXiv:1702.08231, 2017.\n- 【Pruning】Li S, Park J, Tang P T P. [Enabling sparse winograd convolution by native pruning](https://arxiv.org/pdf/1702.08597)[J]. arXiv preprint arXiv:1702.08597, 2017.\n- 【other】Boulch A. [Sharesnet: reducing residual network parameter number by sharing weights](https://arxiv.org/pdf/1702.08782)[J]. arXiv preprint arXiv:1702.08782, 2017.\n- 【Distillation】[Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://arxiv.org/pdf/1703.01780), Antti Tarvainen, Harri Valpola, 2017\n- 【Distillation】[Learning from Noisy Labels with Distillation](https://arxiv.org/abs/1703.02391), Yuncheng Li, Jianchao Yang, Yale Song, Liangliang Cao, Jiebo Luo, Li-Jia Li, 2017 \n- 【Survey】Sze V, Chen Y H, Yang T J, et al. [Efficient processing of deep neural networks: A tutorial and survey](https://arxiv.org/abs/1703.09039)[J]. Proceedings of the IEEE, 2017, 105(12): 2295-2329.\n- 【Structure】Wei Wen, Cong Xu, Chunpeng Wu, Yandan Wang, Yiran Chen, Hai Li .[Coordinating Filters for Faster Deep Neural Networks](https://arxiv.org/pdf/1703.09746) .[J] arXiv preprint arXiv:1703.09746\n- 【Structure】【MobileNet】ndrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam .[MobileNets: Efficient Convolutional Neural Networks for Mobile Vision  Applications](https://arxiv.org/pdf/1704.04861) .[J] arXiv preprint arXiv:1704.04861\n- 【Structure】Fei Wang, Mengqing Jiang, Chen Qian, Shuo Yang, Cheng Li, Honggang Zhang, Xiaogang Wang, Xiaoou Tang .[Residual Attention Network for Image Classification](https://arxiv.org/pdf/1704.06904) .[J] arXiv preprint arXiv:1704.06904\n- 【Pruning】Liu W, Wen Y, Yu Z, et al. [Sphereface: Deep hypersphere embedding for face recognition](http://openaccess.thecvf.com/content_cvpr_2017/papers/Liu_SphereFace_Deep_Hypersphere_CVPR_2017_paper.pdf)[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 212-220.\u003cbr\u003e【code;[isthatyoung/Sphereface-prune](https://github.com/isthatyoung/Sphereface-prune)】\n- 【Quantization】Mellempudi N, Kundu A, Mudigere D, et al. [Ternary neural networks with fine-grained quantization](https://arxiv.org/pdf/1705.01462)[J]. arXiv preprint arXiv:1705.01462, 2017.\n- 【Structure】Louizos C, Ullrich K, Welling M. [Bayesian compression for deep learning](https://arxiv.org/pdf/1705.08665.pdf)[C]//Advances in Neural Information Processing Systems. 2017: 3288-3298.\n- H. Tann, S. Hashemi, I. Bahar, and S. Reda. [Hardwaresoftware codesign of accurate, multiplier-free deep neural networks](https://arxiv.org/pdf/1705.04288). arXiv preprint arXiv:1705.04288, 2017.\n- 【Pruning】Dong X, Chen S, Pan S. [Learning to prune deep neural networks via layer-wise optimal brain surgeon](https://arxiv.org/abs/1705.07565)[C]//Advances in Neural Information Processing Systems. 2017: 4857-4867.\u003cbr\u003e【code:[csyhhu/L-OBS](https://github.com/csyhhu/L-OBS)】\n- H. Mao, S. Han, J. Pool, W. Li, X. Liu, Y. Wang, and W. J. Dally. [Exploring the regularity of sparse structure in convolutional neural networks](https://arxiv.org/pdf/1705.08922). arXiv preprint arXiv:1705.08922, 2017. \n- 【System】Qingqing Cao, Niranjan Balasubramanian, Aruna Balasubramanian .[MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU](https://arxiv.org/pdf/1706.00878) .[J] arXiv preprint arXiv:1706.00878\n- 【Quantization】Denis A. Gudovskiy, Luca Rigazio .[ShiftCNN: Generalized Low-Precision Architecture for Inference of  Convolutional Neural Networks](https://arxiv.org/pdf/1706.02393) .[J] arXiv preprint arXiv:1706.02393\n- 【Structure】Zhe Li, Xiaoyu Wang, Xutao Lv, Tianbao Yang .[SEP-Nets: Small and Effective Pattern Networks](https://arxiv.org/pdf/1706.03912) .[J] arXiv preprint arXiv:1706.03912\n- Zhang Y, Xiang T, Hospedales T M, et al. [Deep mutual learning](https://arxiv.org/pdf/1706.00384.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 4320-4328.\n- 【Structure】【ShuffleNet】Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun .[ShuffleNet: An Extremely Efficient Convolutional Neural Network for  Mobile Devices](https://arxiv.org/pdf/1707.01083) .[J] arXiv preprint arXiv:1707.01083\n- 【Survey】Miguel Á. Carreira-Perpiñán .[Model compression as constrained optimization, with application to  neural nets. Part I: general framework](https://arxiv.org/pdf/1707.01209) .[J] arXiv preprint arXiv:1707.01209\n- 【Pruning】Zehao Huang, Naiyan Wang .[Data-Driven Sparse Structure Selection for Deep Neural Networks](https://arxiv.org/pdf/1707.01213) .[J] arXiv preprint arXiv:1707.01213\u003cbr\u003e【code:[TuSimple/sparse-structure-selection](https://github.com/TuSimple/sparse-structure-selection)】\n- 【Distillation】Zehao Huang, Naiyan Wang .[Like What You Like: Knowledge Distill via Neuron Selectivity Transfer](https://arxiv.org/pdf/1707.01219) .[J] arXiv preprint arXiv:1707.01219\n- 【Distillation】Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang .[DarkRank: Accelerating Deep Metric Learning via Cross Sample  Similarities Transfer](https://arxiv.org/pdf/1707.01220) .[J] arXiv preprint arXiv:1707.01220\n- 【Structure】Ting Zhang, Guo-Jun Qi, Bin Xiao, Jingdong Wang. [Interleaved Group Convolutions for Deep Neural Networks](https://arxiv.org/abs/1707.02725).[J] arXiv preprint arXiv:1707.02725\n- 【Survey】Miguel Á. Carreira-Perpiñán, Yerlan Idelbayev .[Model compression as constrained optimization, with application to  neural nets. Part II: quantization](https://arxiv.org/pdf/1707.04319) .[J] arXiv preprint arXiv:1707.04319\n- 【Binarization】Jeng-Hau Lin, Tianwei Xing, Ritchie Zhao, Zhiru Zhang, Mani Srivastava, Zhuowen Tu, Rajesh K. Gupta .[Binarized Convolutional Neural Networks with Separable Filters for  Efficient Hardware Acceleration](https://arxiv.org/pdf/1707.04693) .[J] arXiv preprint arXiv:1707.04693\n- 【Pruning】Yihui He, Xiangyu Zhang, Jian Sun .[Channel Pruning for Accelerating Very Deep Neural Networks](https://arxiv.org/pdf/1707.06168) .[J] arXiv preprint arXiv:1707.06168\u003cbr\u003e【code:[yihui-he/channel-pruning](https://github.com/yihui-he/channel-pruning);[Eric-mingjie/rethinking-network-pruning](https://github.com/Eric-mingjie/rethinking-network-pruning/tree/master/imagenet)】\n- 【Structure】【Pruning】Jian-Hao Luo, Jianxin Wu, Weiyao Lin .[ThiNet: A Filter Level Pruning Method for Deep Neural Network  Compression](https://arxiv.org/pdf/1707.06342) .[J] arXiv preprint arXiv:1707.06342\u003cbr\u003e【code:[Roll920/ThiNet](https://github.com/Roll920/ThiNet);[Eric-mingjie/rethinking-network-pruning](https://github.com/Eric-mingjie/rethinking-network-pruning/tree/master/imagenet)】\n- 【Structure】Barret Zoph, Vijay Vasudevan, Jonathon Shlens, Quoc V. Le .[Learning Transferable Architectures for Scalable Image Recognition](https://arxiv.org/pdf/1707.07012) .[J] arXiv preprint arXiv:1707.07012\n- 【other】Delmas A, Sharify S, Judd P, et al. [Tartan: Accelerating fully-connected and convolutional layers in deep learning networks by exploiting numerical precision variability](https://arxiv.org/pdf/1707.09068)[J]. arXiv preprint arXiv:1707.09068, 2017.\n- 【Pruning】Frederick Tung, Srikanth Muralidharan, Greg Mori .[Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional  Network with Bayesian Optimization](https://arxiv.org/pdf/1707.09102) .[J] arXiv preprint arXiv:1707.09102\n- 【Quantization】Leng C, Dou Z, Li H, et al. [Extremely low bit neural network: Squeeze the last bit out with admm](https://arxiv.org/abs/1707.09870)[C]//Thirty-Second AAAI Conference on Artificial Intelligence. 2018.\n- 【Distillation】[Rocket Launching: A Universal and Efficient Framework for Training Well-performing Light Net](https://arxiv.org/pdf/1708.04106.pdf), Zihao Liu, Qi Liu, Tao Liu, Yanzhi Wang, Wujie Wen, 2017\n- A. Parashar, M. Rhu, A. Mukkara, A. Puglielli, R. Venkatesan, B. Khailany, J. Emer, S. W. Keckler, and W. J. Dally. [Scnn: An accelerator for compressed-sparse convolutional neural networks](https://arxiv.org/pdf/1708.04485).  arXiv preprint arXiv:1708.04485, 2017. \n- 【Structure】Dawei Li, Xiaolong Wang, Deguang Kong .[DeepRebirth: Accelerating Deep Neural Network Execution on Mobile  Devices](https://arxiv.org/pdf/1708.04728) .[J] arXiv preprint arXiv:1708.04728\n- 【Distillation】[Revisiting knowledge transfer for training object class detectors](https://arxiv.org/pdf/1708.06128.pdf), Jasper Uijlings, Stefan Popov, Vittorio Ferrari, 2017\n- 【Pruning】Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, Changshui Zhang .[Learning Efficient Convolutional Networks through Network Slimming](https://arxiv.org/pdf/1708.06519) .[J] arXiv preprint arXiv:1708.06519\u003cbr\u003e【code:[Eric-mingjie/network-slimming](https://github.com/Eric-mingjie/network-slimming)】\n- 【Distillation】Zheng Xu, Yen-Chang Hsu, Jiawei Huang .[Learning Loss for Knowledge Distillation with Conditional Adversarial  Networks](https://arxiv.org/pdf/1709.00513) .[J] arXiv preprint arXiv:1709.00513\n- 【other】Masana M, van de Weijer J, Herranz L, et al. [Domain-adaptive deep network compression](https://arxiv.org/abs/1709.01041)[C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 4289-4297.\n- Mishra A, Nurvitadhi E, Cook J J, et al. [WRPN: wide reduced-precision networks](https://arxiv.org/pdf/1709.01134)[J]. arXiv preprint arXiv:1709.01134, 2017.\n- 【Distillation】Chong Wang, Xipeng Lan, Yangang Zhang .[Model Distillation with Knowledge Transfer from Face Classification to  Alignment and Verification](https://arxiv.org/pdf/1709.02929) .[J] arXiv preprint arXiv:1709.02929\n- 【Structure】Mohammad Javad Shafiee, Brendan Chywl, Francis Li, Alexander Wong .[Fast YOLO: A Fast You Only Look Once System for Real-time Embedded  Object Detection in Video](https://arxiv.org/pdf/1709.05943) .[J] arXiv preprint arXiv:1709.05943\n- 【Train】Ashok A, Rhinehart N, Beainy F, et al. [N2n learning: Network to network compression via policy gradient reinforcement learning](https://arxiv.org/pdf/1709.06030)[J]. arXiv preprint arXiv:1709.06030, 2017.\n- 【Pruning】Michael Zhu, Suyog Gupta .[To prune, or not to prune: exploring the efficacy of pruning for model  compression](https://arxiv.org/pdf/1710.01878) .[J] arXiv preprint arXiv:1710.01878\n- 【Distillation】Raphael Gontijo Lopes, Stefano Fenu, Thad Starner .[Data-Free Knowledge Distillation for Deep Neural Networks](https://arxiv.org/pdf/1710.07535) .[J] arXiv preprint arXiv:1710.07535\n- 【Survey】Yu Cheng, Duo Wang, Pan Zhou, Tao Zhang .[A Survey of Model Compression and Acceleration for Deep Neural Networks](https://arxiv.org/pdf/1710.09282) .[J] arXiv preprint arXiv:1710.09282\n- 【Distillation】Zhi Zhang, Guanghan Ning, Zhihai He .[Knowledge Projection for Deep Neural Networks](https://arxiv.org/pdf/1710.09505) .[J] arXiv preprint arXiv:1710.09505\n- 【Structure】Mohammad Ghasemzadeh, Mohammad Samragh, Farinaz Koushanfar .[ReBNet: Residual Binarized Neural Network](https://arxiv.org/pdf/1711.01243) .[J] arXiv preprint arXiv:1711.01243\n- 【Distillation】Elliot J. Crowley, Gavin Gray, Amos Storkey .[Moonshine: Distilling with Cheap Convolutions](https://arxiv.org/pdf/1711.02613) .[J] arXiv preprint arXiv:1711.02613\n- 【Quantization】Reagen B, Gupta U, Adolf R, et al. [Weightless: Lossy weight encoding for deep neural network compression](https://arxiv.org/pdf/1711.04686)[J]. arXiv preprint arXiv:1711.04686, 2017.\n- 【Distillation】Mishra A, Marr D. [Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy](https://arxiv.org/pdf/1711.05852)[J]. arXiv preprint arXiv:1711.05852, 2017.\n- 【Pruning】Ruichi Yu, Ang Li, Chun-Fu Chen, Jui-Hsin Lai, Vlad I. Morariu, Xintong Han, Mingfei Gao, Ching-Yung Lin, Larry S. Davis .[NISP: Pruning Networks using Neuron Importance Score Propagation](https://arxiv.org/pdf/1711.05908) .[J] arXiv preprint arXiv:1711.05908\n- 【Pruning】iel Gordon, Elad Eban, Ofir Nachum, Bo Chen, Tien-Ju Yang, Edward Choi .[MorphNet: Fast \u0026 Simple Resource-Constrained Structure Learning of Deep  Networks](https://arxiv.org/pdf/1711.06798) .[J] arXiv preprint arXiv:1711.06798\u003cbr\u003e【code:[google-research/morph-net](https://github.com/google-research/morph-net)】\n- 【System】Stylianos I. Venieris, Christos-Savvas Bouganis .[fpgaConvNet: A Toolflow for Mapping Diverse Convolutional Neural  Networks on Embedded FPGAs](https://arxiv.org/pdf/1711.08740) .[J] arXiv preprint arXiv:1711.08740\n- 【Structure】Gao Huang, Shichen Liu, Laurens van der Maaten, Kilian Q. Weinberger .[CondenseNet: An Efficient DenseNet using Learned Group Convolutions](https://arxiv.org/pdf/1711.09224) .[J] arXiv preprint arXiv:1711.09224\n- 【Quantization】Zhou Y, Moosavi-Dezfooli S M, Cheung N M, et al. [Adaptive quantization for deep neural network](https://arxiv.org/abs/1712.01048)[C]//Thirty-Second AAAI Conference on Artificial Intelligence. 2018.\n- [Learning Sparse Neural Networks through L0 Regularization](https://arxiv.org/abs/1712.01312) .[J] arXiv preprint arXiv:1711.01312\n- 【Train】Lin Y, Han S, Mao H, et al. [Deep gradient compression: Reducing the communication bandwidth for distributed training](https://arxiv.org/pdf/1712.01887.pdf)[J]. arXiv preprint arXiv:1712.01887, 2017.\n- 【Low Rank】ndrew Tulloch, Yangqing Jia .[High performance ultra-low-precision convolutions on mobile devices](https://arxiv.org/pdf/1712.02427) .[J] arXiv preprint arXiv:1712.02427\n- 【Train】Chen C Y, Choi J, Brand D, et al. [Adacomp: Adaptive residual gradient compression for data-parallel distributed training](https://arxiv.org/abs/1712.02679)[C]//Thirty-Second AAAI Conference on Artificial Intelligence. 2018.\n- 【Structure】【StrassenNets】Tschannen M, Khanna A, Anandkumar A. [StrassenNets: Deep learning with a multiplication budget](https://arxiv.org/pdf/1712.03942)[J]. arXiv preprint arXiv:1712.03942, 2017.\n- 【Distillation】[Data Distillation: Towards Omni-Supervised Learning](https://arxiv.org/pdf/1712.04440.pdf), Ilija Radosavovic, Piotr Dollár, Ross Girshick, Georgia Gkioxari, Kaiming He, 2017\n- 【Decomposition】Ye J, Wang L, Li G, et al. [Learning compact recurrent neural networks with block-term tensor decomposition](https://arxiv.org/abs/1712.05134)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 9378-9387.\n- 【Quantization】Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, Dmitry Kalenichenko .[Quantization and Training of Neural Networks for Efficient  Integer-Arithmetic-Only Inference](https://arxiv.org/pdf/1712.05877) .[J] arXiv preprint arXiv:1712.05877\n\n\n### 2018\n- 【Thesis】[Algorithms for speeding up convolutional neural networks](https://www.skoltech.ru/app/data/uploads/2018/10/Thesis-Final.pdf)\n- 【Survey】Cheng Y, Wang D, Zhou P, et al. [Model compression and acceleration for deep neural networks: The principles, progress, and challenges](https://www.gwern.net/docs/ai/2018-cheng.pdf)[J]. IEEE Signal Processing Magazine, 2018, 35(1): 126-136.\n- 【Structure】【ChannelNets】Gao H, Wang Z, Ji S. [Channelnets: Compact and efficient convolutional neural networks via channel-wise convolutions](https://papers.nips.cc/paper/7766-channelnets-compact-and-efficient-convolutional-neural-networks-via-channel-wise-convolutions.pdf)[C]//Advances in Neural Information Processing Systems. 2018: 5197-5205.\u003cbr\u003e【code:[HongyangGao/ChannelNets](https://github.com/HongyangGao/ChannelNets)】\n- 【Structure】【Shift】Wu B, Wan A, Yue X, et al. [Shift: A zero flop, zero parameter alternative to spatial convolutions](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Shift_A_Zero_CVPR_2018_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 9127-9135.\u003cbr\u003e【code:[alvinwan/shiftresnet-cifar](https://github.com/alvinwan/shiftresnet-cifar)】\n- 【Quantization】Son S, Nah S, Mu Lee K. [Clustering convolutional kernels to compress deep neural networks](http://openaccess.thecvf.com/content_ECCV_2018/papers/Sanghyun_Son_Clustering_Kernels_for_ECCV_2018_paper.pdf)[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 216-232.\n- 【Quantization】Yu T, Yuan J, Fang C, et al. [Product quantization network for fast image retrieval](http://openaccess.thecvf.com/content_ECCV_2018/papers/Tan_Yu_Product_Quantization_Network_ECCV_2018_paper.pdf)[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 186-201.\n- 【Quantization】Achterhold J, Koehler J M, Schmeink A, et al.[Variational network quantization](https://openreview.net/pdf?id=ry-TW-WAb)[J]. 2018.\n- 【Quantization】Martinez J, Zakhmi S, Hoos H H, et al. [LSQ++: Lower running time and higher recall in multi-codebook quantization](http://openaccess.thecvf.com/content_ECCV_2018/papers/Julieta_Martinez_LSQ_lower_runtime_ECCV_2018_paper.pdf)[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 491-506. \n- 【Quantization】Zhou A, Yao A, Wang K, et al. [Explicit loss-error-aware quantization for low-bit deep neural networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Explicit_Loss-Error-Aware_Quantization_CVPR_2018_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 9426-9435.\n- 【Quantization】Nakanishi K, Maeda S, Miyato T, et al. [Adaptive Sample-space \u0026 Adaptive Probability coding: a neural-network based approach for compression](https://openreview.net/pdf?id=HkzNXhC9KQ)[J]. 2018.\n- 【Quantization】Mukherjee L, Ravi S N, Peng J, et al. [A Biresolution Spectral Framework for Product Quantization](http://openaccess.thecvf.com/content_cvpr_2018/papers/Mukherjee_A_Biresolution_Spectral_CVPR_2018_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 3329-3338.\n- 【Quantization】Zhou Y, Moosavi-Dezfooli S M, Cheung N M, et al. [Adaptive quantization for deep neural network](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPDFInterstitial/16248/16774)[C]//Thirty-Second AAAI Conference on Artificial Intelligence. 2018.\n- 【Quantization】Li D, Wang X, Kong D. [Deeprebirth: Accelerating deep neural network execution on mobile devices](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPDFInterstitial/16652/15946)[C]//Thirty-Second AAAI Conference on Artificial Intelligence. 2018.\n- 【Quantization】Wang P, Hu Q, Zhang Y, et al. [Two-step quantization for low-bit neural networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Two-Step_Quantization_for_CVPR_2018_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 4376-4384.\n- 【Quantization】Leng C, Dou Z, Li H, et al. [Extremely low bit neural network: Squeeze the last bit out with admm](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPDFInterstitial/16767/16728)[C]//Thirty-Second AAAI Conference on Artificial Intelligence. 2018.\n- 【other】Chen T, Lin L, Zuo W, et al. [Learning a wavelet-like auto-encoder to accelerate deep neural networks](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/download/16655/16254)[C]//Thirty-Second AAAI Conference on Artificial Intelligence. 2018.\n- 【other】He X, Cheng J. [Learning Compression from Limited Unlabeled Data](http://openaccess.thecvf.com/content_ECCV_2018/papers/Xiangyu_He_Learning_Compression_from_ECCV_2018_paper.pdf)[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 752-769.\n- 【other】Dai L, Tang L, Xie Y, et al. [Designing by training: acceleration neural network for fast high-dimensional convolution](https://papers.nips.cc/paper/7420-designing-by-training-acceleration-neural-network-for-fast-high-dimensional-convolution.pdf)[C]//Advances in Neural Information Processing Systems. 2018: 1466-1475.\n- 【other】Cicek S, Fawzi A, Soatto S. [Saas: Speed as a supervisor for semi-supervised learning](http://openaccess.thecvf.com/content_ECCV_2018/papers/Safa_Cicek_SaaS_Speed_as_ECCV_2018_paper.pdf)[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 149-163.\n- 【other】Chen W, Wilson J, Tyree S, et al. [Compressing convolutional neural networks in the frequency domain](https://dl.acm.org/ft_gateway.cfm?id=2939839\u0026type=pdf)[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016: 1475-1484.\n- 【other】Lim C H. [An efficient pruning algorithm for robust isotonic regression](http://papers.nips.cc/paper/7306-an-efficient-pruning-algorithm-for-robust-isotonic-regression.pdf)[C]//Advances in Neural Information Processing Systems. 2018: 219-229.\n- 【Train】Wang N, Choi J, Brand D, et al. [Training deep neural networks with 8-bit floating point numbers](https://papers.nips.cc/paper/7994-training-deep-neural-networks-with-8-bit-floating-point-numbers.pdf)[C]//Advances in neural information processing systems. 2018: 7675-7684.\n- 【Pruning】Fu Y, Zhang S, Li D, et al. [pruning in training: learning and ranking sparse connections in deep convolutional networks](https://openreview.net/pdf?id=r1GgDj0cKX)[J]. 2018.\n- 【Pruning】Gao W, Wei Y, Li Q, et al. [pruning with hints: an efficient framework for model acceleration](https://openreview.net/pdf?id=Hyffti0ctQ)[J]. 2018.\n- 【Pruning】Tung F, Mori G. [Clip-q: Deep network compression learning by in-parallel pruning-quantization](http://www.sfu.ca/~ftung/papers/clipq_cvpr18.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 7873-7882.\n- 【Pruning】Zeng W, Urtasun R. [MLPrune: Multi-Layer Pruning for Automated Neural Network Compression](https://openreview.net/pdf?id=r1g5b2RcKm)[J]. 2018.\n- 【Pruning】Carreira-Perpinán M A, Idelbayev Y. [“Learning-Compression” Algorithms for Neural Net Pruning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Carreira-Perpinan_Learning-Compression_Algorithms_for_CVPR_2018_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 8532-8541.\n- 【Pruning】[Cumulative Saliency based Globally Balanced Filter Pruning For Efficient Convolutional Neural Networks ](https://openreview.net/forum?id=H1fevoAcKX)\n- 【Pruning】Yeh C K, Yen I E H, Chen H Y, et al. [deep-trim: revisiting l1 regularization for connection pruning of deep network](https://openreview.net/pdf?id=r1exVhActQ)[J]. 2018.\n- 【Pruning】Zhang X, Zhu Z, Xu Z. [Learning to Search Efficient DenseNet with Layer-wise Pruning](https://openreview.net/pdf?id=r1fWmnR5tm)[J]. 2018.\n- 【Pruning】Liu Z, Xu J, Peng X, et al. [Frequency-domain dynamic pruning for convolutional neural networks](https://papers.nips.cc/paper/7382-frequency-domain-dynamic-pruning-for-convolutional-neural-networks.pdf)[C]//Advances in Neural Information Processing Systems. 2018: 1043-1053.\n- 【Pruning】Evci U, Le Roux N, Castro P, et al. [Mean Replacement Pruning](https://openreview.net/pdf?id=BJxRVnC5Fm)[J]. 2018.\n- 【Pruning】Svoboda F, Liberis E, Lane N D. [In search of theoretically grounded pruning](https://openreview.net/pdf?id=SkfQAiA9YX)[J]. 2018.\n- 【Pruning】He, Yihui, et al. [AMC: AutoML for model compression and acceleration on mobile devices](http://openaccess.thecvf.com/content_ECCV_2018/papers/Yihui_He_AMC_Automated_Model_ECCV_2018_paper.pdf) Proceedings of the European Conference on Computer Vision (ECCV). 2018.\n- 【Pruning】Chen C, Tung F, Vedula N, et al. [Constraint-aware deep neural network compression](http://openaccess.thecvf.com/content_ECCV_2018/papers/Changan_Chen_Constraints_Matter_in_ECCV_2018_paper.pdf)[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 400-415.\u003cbr\u003e【code:[ChanganVR/ConstraintAwareCompression](https://github.com/ChanganVR/ConstraintAwareCompression)】\n- 【Pruning】Carreira-Perpinán, Miguel A., and Yerlan Idelbayev. [“Learning-Compression” Algorithms for Neural Net Pruning](http://faculty.ucmerced.edu/mcarreira-perpinan/papers/cvpr18.pdf) Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.\n- 【Pruning】Yang Q, Wen W, Wang Z, et al. [Integral Pruning on Activations and Weights for Efficient Neural Networks](https://openreview.net/pdf?id=HyevnsCqtQ)[J]. 2018.\n- 【Distillation】[Self-supervised knowledge distillation using singular value decomposition](http://openaccess.thecvf.com/content_ECCV_2018/html/SEUNG_HYUN_LEE_Self-supervised_Knowledge_Distillation_ECCV_2018_paper.html), Seung Hyun Lee, Dae Ha Kim, Byung Cheol Song, 2018\n- 【Distillation】Park S U, Kwak N. [FEED: Feature-level Ensemble Effect for knowledge Distillation](https://openreview.net/pdf?id=BJxYEsAqY7)[J]. 2018.\n- 【Distillation】Tao Z, Xia Q, Li Q. [knowledge distill via learning neuron manifold](https://openreview.net/pdf?id=SJlYcoCcKX)[J]. 2018.\n- 【Distillation】[Exploration by random distillation](https://openreview.net/forum?id=H1lJJnR5Ym)\n -【Distillation】Wang X, Zhang R, Sun Y, et al. [KDGAN: knowledge distillation with generative adversarial networks](https://papers.nips.cc/paper/7358-kdgan-knowledge-distillation-with-generative-adversarial-networks.pdf)[C]//Advances in Neural Information Processing Systems. 2018: 775-786.\n- Sakr C, Choi J, Wang Z, et al. [True Gradient-Based Training of Deep Binary Activated Neural Networks Via Continuous Binarization](http://sakr2.web.engr.illinois.edu/papers/2018/icassp_binarization_final.pdf)[C]//2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018: 2346-2350.\n- Su J, Li J, Bhattacharjee B, et al. [Exploiting Invariant Structures for Compression in Neural Networks](https://openreview.net/pdf?id=rkl85oRqYX)[J]. 2018.\n- Suau X, Zappella L, Apostoloff N. [Network compression using correlation analysis of layer responses](https://openreview.net/pdf?id=rkl42iA5t7)[J]. 2018.\n- [Architecture Compression](https://openreview.net/forum?id=BygGNnCqKQ)\n- Darlow L N, Storkey A. [What Information Does a ResNet Compress?](https://openreview.net/pdf?id=HklbTjRcKX)[J]. 2018.\n- Shwartz-Ziv R, Painsky A, Tishby N. [representation compression and generalization in deep neural networks](https://openreview.net/pdf?id=SkeL6sCqK7)[J]. 2018.\n- Zhuang B, Shen C, Tan M, et al. [Towards effective low-bitwidth convolutional neural networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhuang_Towards_Effective_Low-Bitwidth_CVPR_2018_paper.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 7920-7928.\u003cbr\u003e【code:[nowgood/QuantizeCNNModel](https://github.com/nowgood/QuantizeCNNModel)】\n- Liu Z, Wu B, Luo W, et al. [Bi-real net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm](http://openaccess.thecvf.com/content_ECCV_2018/papers/zechun_liu_Bi-Real_Net_Enhancing_ECCV_2018_paper.pdf)[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 722-737.\u003cbr\u003e【code:[liuzechun/Bi-Real-net](https://github.com/liuzechun/Bi-Real-net)】\n- G. Li, F. Li, T. Zhao, and J. Cheng. [Block convolution: Towards memory-efficeint inference of large-scale cnns on fpga]. In Design Automation and Test in Europe, 2018. \n- Schindler G, Roth W, Pernkopf F, et al. [N-Ary Quantization for CNN Model Compression and Inference Acceleration](https://openreview.net/pdf?id=HylDpoActX)[J]. 2018.\n- P. Wang, Q. Hu, Z. Fang, C. Zhao, and J. Cheng. [Deepsearch: A fast image search framework for mobile devices](http://159.226.21.68/bitstream/173211/20896/1/TOMM1401-06.pdf). ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 14, 2018. \n- Q. Hu, P.Wang, and J. Cheng. [From hashing to cnns: Training binary weight networks via hashing](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPDFInterstitial/16466/16691). In AAAI, February 2018. \n  J. Cheng, J. Wu, C. Leng, Y. Wang, and Q. Hu. [Quantized cnn: A unified approach to accelerate and compress convolutional networks]. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), PP:1–14. \n- 【Structure】【MobileNetV2】Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen .[MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/pdf/1801.04381) .[J] arXiv preprint arXiv:1801.04381\u003cbr\u003e【code:[tensorflow/models](https://github.com/tensorflow/models/tree/master/research/slim/nets/mobilenet)】\n- Theodore S. Nowak, Jason J. Corso .[Deep Net Triage: Analyzing the Importance of Network Layers via  Structural Compression](https://arxiv.org/pdf/1801.04651) .[J] arXiv preprint arXiv:1801.04651.\n- Lucas Theis, Iryna Korshunova, Alykhan Tejani, Ferenc Huszár .[Faster gaze prediction with dense networks and Fisher pruning](https://arxiv.org/pdf/1801.05787) .[J] arXiv preprint arXiv:1801.05787.\n- Brian Trippe, Richard Turner .[Overpruning in Variational Bayesian Neural Networks](https://arxiv.org/pdf/1801.06230) .[J] arXiv preprint arXiv:1801.06230.\n- Qiangui Huang, Kevin Zhou, Suya You, Ulrich Neumann .[Learning to Prune Filters in Convolutional Neural Networks](https://arxiv.org/pdf/1801.07365) .[J] arXiv preprint arXiv:1801.07365.\n- 【Distillation】Sarah Tan, Rich Caruana, Giles Hooker, Albert Gordo .[Transparent Model Distillation](https://arxiv.org/pdf/1801.08640) .[J] arXiv preprint arXiv:1801.08640.\n- Congzheng Song, Yiming Sun .[Kernel Distillation for Gaussian Processes](https://arxiv.org/pdf/1801.10273) .[J] arXiv preprint arXiv:1801.10273.\n- Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra, Balaraman Ravindran .[Recovering from Random Pruning: On the Plasticity of Deep Convolutional  Neural Networks](https://arxiv.org/pdf/1801.10447) .[J] arXiv preprint arXiv:1801.10447.\n- Jialiang Guo, Bo Zhou, Xiangrui Zeng, Zachary Freyberg, Min Xu .[Model compression for faster structural separation of macromolecules  captured by Cellular Electron Cryo-Tomography](https://arxiv.org/pdf/1801.10597) .[J] arXiv preprint arXiv:1801.10597.\n- 【Pruning】Jianbo Ye, Xin Lu, Zhe Lin, James Z. Wang .[Rethinking the Smaller-Norm-Less-Informative Assumption in Channel  Pruning of Convolution Layers](https://arxiv.org/pdf/1802.00124) .[J] arXiv preprint arXiv:1802.00124.\u003cbr\u003e【code:[jack-willturner/batchnorm-pruning](https://github.com/jack-willturner/batchnorm-pruning)】\n- 【Quantization】Chen Xu, Jianqiang Yao, Zhouchen Lin, Wenwu Ou, Yuanbin Cao, Zhirong Wang, Hongbin Zha .[Alternating Multi-bit Quantization for Recurrent Neural Networks](https://arxiv.org/pdf/1802.00150) .[J] arXiv preprint arXiv:1802.00150.\n- Yixing Li, Fengbo Ren .[Build a Compact Binary Neural Network through Bit-level Sensitivity and  Data Pruning](https://arxiv.org/pdf/1802.00904) .[J] arXiv preprint arXiv:1802.00904.\n- 【Survey】Jian Cheng, Peisong Wang, Gang Li, Qinghao Hu, Hanqing Lu .[Recent Advances in Efficient Computation of Deep Convolutional Neural  Networks](https://arxiv.org/pdf/1802.00939) .[J] arXiv preprint arXiv:1802.00939\n- Yoojin Choi, Mostafa El-Khamy, Jungwon Lee .[Universal Deep Neural Network Compression](https://arxiv.org/pdf/1802.02271) .[J] arXiv preprint arXiv:1802.02271.\n- Md Zahangir Alom, Adam T Moody, Naoya Maruyama, Brian C Van Essen, Tarek M. Taha .[Effective Quantization Approaches for Recurrent Neural Networks](https://arxiv.org/pdf/1802.02615) .[J] arXiv preprint arXiv:1802.02615.\n- 【Distillation】[Efficient Neural Architecture Search via Parameters Sharing](https://arxiv.org/pdf/1802.03268), Hieu Pham, Melody Y. Guan, Barret Zoph, Quoc V. Le, Jeff Dean, 2018\n- 【Pruning】Yihui He, Song Han .[ADC: Automated Deep Compression and Acceleration with Reinforcement  Learning](https://arxiv.org/pdf/1802.03494) .[J] arXiv preprint arXiv:1802.03494.\u003cbr\u003e【code:[Tencent/PocketFlow#channel-pruning](https://github.com/Tencent/PocketFlow#channel-pruning);[mit-han-lab/amc-release](https://github.com/mit-han-lab/amc-release);[mit-han-lab/amc-compressed-models](https://github.com/mit-han-lab/amc-compressed-models)】\n- 【Quantization】Yukun Ding, Jinglan Liu, Yiyu Shi .[On the Universal Approximability of Quantized ReLU Neural Networks](https://arxiv.org/pdf/1802.03646) .[J] arXiv preprint arXiv:1802.03646\n- 【Structured】Qin Z, Zhang Z, Chen X, et al. [Fd-mobilenet: Improved mobilenet with a fast downsampling strategy](https://arxiv.org/pdf/1802.03750)[C]//2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018: 1363-1367.\n- Jeff Zhang, Kartheek Rangineni, Zahra Ghodsi, Siddharth Garg .[ThUnderVolt: Enabling Aggressive Voltage Underscaling and Timing Error  Resilience for Energy Efficient Deep Neural Network Accelerators](https://arxiv.org/pdf/1802.03806) .[J] arXiv preprint arXiv:1802.03806.\n- Jeff Zhang, Tianyu Gu, Kanad Basu, Siddharth Garg .[Analyzing and Mitigating the Impact of Permanent Faults on a Systolic  Array Based Neural Network Accelerator](https://arxiv.org/pdf/1802.04657) .[J] arXiv preprint arXiv:1802.04657.\n- 【Quantization】Wu S, Li G, Chen F, et al.[Training and Inference with Integers in Deep Neural Networks](https://arxiv.org/pdf/1802.04680) .[J] arXiv preprint arXiv:1802.04680\u003cbr\u003e【code:[boluoweifenda/WAGE](https://github.com/boluoweifenda/WAGE)】\n- Luiz M Franca-Neto .[Field-Programmable Deep Neural Network (DNN) Learning and Inference  accelerator: a concept](https://arxiv.org/pdf/1802.04899) .[J] arXiv preprint arXiv:1802.04899.\n- 【other】Jia Z, Lin S, Qi C R, et al. [Exploring hidden dimensions in parallelizing convolutional neural networks](https://arxiv.org/pdf/1802.04924)[J]. arXiv preprint arXiv:1802.04924, 2018.\n- 【other】Jangho Kim, SeoungUK Park, Nojun Kwak .[Paraphrasing Complex Network: Network Compression via Factor Transfer](https://arxiv.org/pdf/1802.04977) .[J] arXiv preprint arXiv:1802.04977.\n- 【Quantization】Dai L, Tang L, Xie Y, et al. [Designing by training: acceleration neural network for fast high-dimensional convolution](https://papers.nips.cc/paper/7420-designing-by-training-acceleration-neural-network-for-fast-high-dimensional-convolution.pdf)[C]//Advances in Neural Information Processing Systems. 2018: 1466-1475.\n- Qi Liu, Tao Liu, Zihao Liu, Yanzhi Wang, Yier Jin, Wujie Wen .[Security Analysis and Enhancement of Model Compressed Deep Learning  Systems under Adversarial Attacks](https://arxiv.org/pdf/1802.05193) .[J] arXiv preprint arXiv:1802.05193.\n- 【other】Sanjeev Arora, Rong Ge, Behnam Neyshabur, Yi Zhang .[Stronger generalization bounds for deep nets via a compression approach](https://arxiv.org/pdf/1802.05296) .[J] arXiv preprint arXiv:1802.05296.\n- 【Quantization】Antonio Polino, Razvan Pascanu, Dan Alistarh .[Model compression via distillation and quantization](https://arxiv.org/pdf/1802.05668) .[J] arXiv preprint arXiv:1802.05668.\u003cbr\u003e【code:[antspy/quantized_distillation)](https://github.com/antspy/quantized_distillation)】\n- Tianyun Zhang, Shaokai Ye, Yipeng Zhang, Yanzhi Wang, Makan Fardad .[Systematic Weight Pruning of DNNs using Alternating Direction Method of  Multipliers](https://arxiv.org/pdf/1802.05747) .[J] arXiv preprint arXiv:1802.05747.\n- 【other】Arora S, Cohen N, Hazan E. [On the optimization of deep networks: Implicit acceleration by overparameterization](https://arxiv.org/pdf/1802.06509)[J]. arXiv preprint arXiv:1802.06509, 2018.\n- Jiangyan Yi, Jianhua Tao, Zhengqi Wen, Bin Liu .[Distilling Knowledge Using Parallel Data for Far-field Speech  Recognition](https://arxiv.org/pdf/1802.06941) .[J] arXiv preprint arXiv:1802.06941.\n- Matthew Sotoudeh, Sara S. Baghsorkhi .[DeepThin: A Self-Compressing Library for Deep Neural Networks](https://arxiv.org/pdf/1802.06944) .[J] arXiv preprint arXiv:1802.06944.\n- Ming Yu, Zhaoran Wang, Varun Gupta, Mladen Kolar .[Recovery of simultaneous low rank and two-way sparse coefficient  matrices, a nonconvex approach](https://arxiv.org/pdf/1802.06967) .[J] arXiv preprint arXiv:1802.06967.\n- Babajide O. Ayinde, Jacek M. Zurada .[Building Efficient ConvNets using Redundant Feature Pruning](https://arxiv.org/pdf/1802.07653) .[J] arXiv preprint arXiv:1802.07653.\n- 【Binarization】McDonnell M D. [Training wide residual networks for deployment using a single bit for each weight](https://arxiv.org/pdf/1802.08530)[J]. arXiv preprint arXiv:1802.08530, 2018.\u003cbr\u003e【code:[szagoruyko/binary-wide-resnet](https://github.com/szagoruyko/binary-wide-resnet)】\n- 【Quantization】Lu Hou, James T. Kwok .[Loss-aware Weight Quantization of Deep Networks](https://arxiv.org/pdf/1802.08635) .[J] arXiv preprint arXiv:1802.08635.\n- 【Deconvolution】Wenqi Wang, Yifan Sun, Brian Eriksson, Wenlin Wang, Vaneet Aggarwal .[Wide Compression: Tensor Ring Nets](https://arxiv.org/pdf/1802.09052) .[J] arXiv preprint arXiv:1802.09052.\n- Jinglan Liu, Jiaxin Zhang, Yukun Ding, Xiaowei Xu, Meng Jiang, Yiyu Shi .[PBGen: Partial Binarization of Deconvolution-Based Generators for Edge  Intelligence](https://arxiv.org/pdf/1802.09153) .[J] arXiv preprint arXiv:1802.09153.\n- 【Other】Bin Dai, Chen Zhu, David Wipf .[Compressing Neural Networks using the Variational Information Bottleneck](https://arxiv.org/pdf/1802.10399) .[J] arXiv preprint arXiv:1802.10399.\n- Andros Tjandra, Sakriani Sakti, Satoshi Nakamura .[Tensor Decomposition for Compressing Recurrent Neural Network](https://arxiv.org/pdf/1802.10410) .[J] arXiv preprint arXiv:1802.10410.\n-  .[Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning](https://arxiv.org/pdf/1803.00184) .[J] arXiv preprint arXiv:1803.00184.\n- 【Quantization】.[Deep Neural Network Compression with Single and Multiple Level  Quantization](https://arxiv.org/pdf/1803.03289) .[J] arXiv preprint arXiv:1803.03289.\n- 【Pruning】.[The Lottery Ticket Hypothesis: Training Pruned Neural Networks](https://arxiv.org/pdf/1803.03635) .[J] arXiv preprint arXiv:1803.03635.\u003cbr\u003e【code:[google-research/lottery-ticket-hypothesis](https://github.com/google-research/lottery-ticket-hypothesis)】\n- 【Distillation】.[Interpreting Deep Classifier by Visual Distillation of Dark Knowledge](https://arxiv.org/pdf/1803.04042) .[J] arXiv preprint arXiv:1803.04042.\n-  .[FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees](https://arxiv.org/pdf/1803.04239) .[J] arXiv preprint arXiv:1803.04239.\n- 【Distillation】[Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling](https://arxiv.org/pdf/1803.04687.pdf), Abrar H. Abdulnabi, Bing Shuai, Zhen Zuo, Lap-Pui Chau, Gang Wang, 2018\n-  【Quantization】.[Quantization of Fully Convolutional Networks for Accurate Biomedical  Image Segmentation](https://arxiv.org/pdf/1803.04907) .[J] arXiv preprint arXiv:1803.04907.\n- 【Distillation】[Defensive Collaborative Multi-task Training - Defending against Adversarial Attack towards Deep Neural Networks](https://arxiv.org/pdf/1803.05123), Derek Wang, Chaoran Li, Sheng Wen, Yang Xiang, Wanlei Zhou, Surya Nepal, 2018 \n- Dong Wang, Lei Zhou, Xueni Zhang, Xiao Bai, Jun Zhou .[Exploring Linear Relationship in Feature Map Subspace for ConvNets  Compression](https://arxiv.org/pdf/1803.05729) .[J] arXiv preprint arXiv:1803.05729.\n- 【Distillation】[Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples](https://arxiv.org/pdf/1803.05787), Zihao Liu, Qi Liu, Tao Liu, Yanzhi Wang, Wujie Wen, 2018\n- 【Distillation】[Deep Co-Training for Semi-Supervised Image Recognition](https://arxiv.org/pdf/1803.05984), Siyuan Qiao, Wei Shen, Zhishuai Zhang, Bo Wang, Alan Yuille, 2018\n- Shuo Wang, Zhe Li, Caiwen Ding, Bo Yuan, Yanzhi Wang, Qinru Qiu, Yun Liang\n- 【Train】Tang H, Gan S, Zhang C, et al. [Communication compression for decentralized training](https://arxiv.org/abs/1803.06443)[C]//Advances in Neural Information Processing Systems. 2018: 7652-7662.\n .[C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques  on FPGAs](https://arxiv.org/pdf/1803.06305) .[J] arXiv preprint arXiv:1803.06305.\n- Qing Tian, Tal Arbel, James J. Clark .[Fisher Pruning of Deep Nets for Facial Trait Classification](https://arxiv.org/pdf/1803.08134) .[J] arXiv preprint arXiv:1803.08134.\n- Tao Sheng, Chen Feng, Shaojie Zhuo, Xiaopeng Zhang, Liang Shen, Mickey Aleksic .[A Quantization-Friendly Separable Convolution for MobileNets](https://arxiv.org/pdf/1803.08607) .[J] arXiv preprint arXiv:1803.08607.\n- Maksym Kholiavchenko .[Iterative Low-Rank Approximation for CNN Compression](https://arxiv.org/pdf/1803.08995) .[J] arXiv preprint arXiv:1803.08995.\n- 【Distillation】Zheng Hui, Xiumei Wang, Xinbo Gao .[Fast and Accurate Single Image Super-Resolution via Information  Distillation Network](https://arxiv.org/pdf/1803.09454) .[J] arXiv preprint arXiv:1803.09454.\n- Jongwon Choi, Hyung Jin Chang, Tobias Fischer, Sangdoo Yun, Kyuewang Lee, Jiyeoup Jeong, Yiannis Demiris, Jin Young Choi .[Context-aware Deep Feature Compression for High-speed Visual Tracking](https://arxiv.org/pdf/1803.10537) .[J] arXiv preprint arXiv:1803.10537.\n- 【Structure】Gholami A, Kwon K, Wu B, et al. [Squeezenext: Hardware-aware neural network design](https://arxiv.org/pdf/1803.10615.pdf)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2018: 1638-1647.\n- Vasileios Belagiannis, Azade Farshad, Fabio Galasso .[Adversarial Network Compression](https://arxiv.org/pdf/1803.10750) .[J] arXiv preprint arXiv:1803.10750.\n- Ameya Prabhu, Vishal Batchu, Sri Aurobindo Munagala, Rohit Gajawada, Anoop Namboodiri .[Distribution-Aware Binarization of Neural Networks for Sketch  Recognition](https://arxiv.org/pdf/1804.02941) .[J] arXiv preprint arXiv:1804.02941.\n- 【Distillation】[Large scale distributed neural network training through online distillation](https://arxiv.org/abs/1804.03235), Rohan Anil, Gabriel Pereyra, Alexandre Passos, Robert Ormandi, George E. Dahl, Geoffrey E. Hinton, 2018\n- 【Pruning】Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Jian Tang, Wujie Wen, Makan Fardad, Yanzhi Wang .[A Systematic DNN Weight Pruning Framework using Alternating Direction  Method of Multipliers](https://arxiv.org/pdf/1804.03294) .[J] arXiv preprint arXiv:1804.03294.\u003cbr\u003e【code:[KaiqiZhang/admm-pruning](https://github.com/KaiqiZhang/admm-pruning)】\n- Guanglu Song, Yu Liu, Ming Jiang, Yujie Wang, Junjie Yan, Biao Leng .[Beyond Trade-off: Accelerate FCN-based Face Detector with Higher  Accuracy](https://arxiv.org/pdf/1804.05197) .[J] arXiv preprint arXiv:1804.05197.\n- Cenk Baykal, Lucas Liebenwein, Igor Gilitschenski, Dan Feldman, Daniela Rus .[Data-Dependent Coresets for Compressing Neural Networks with  Applications to Generalization Bounds](https://arxiv.org/pdf/1804.05345) .[J] arXiv preprint arXiv:1804.05345.\n- Wenda Zhou, Victor Veitch, Morgane Austern, Ryan P. Adams, Peter Orbanz .[Compressibility and Generalization in Large-Scale Deep Learning](https://arxiv.org/pdf/1804.05862) .[J] arXiv preprint arXiv:1804.05862.\n- 【Structured】Xie G, Wang J, Zhang T, et al. [Interleaved structured sparse convolutional neural networks](https://arxiv.org/abs/1804.06202)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 8847-8856.\n- Xu J, Nie Y, Wang P, et al. [Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving](https://arxiv.org/pdf/1804.06332)[C]//2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019: 2379-2384.\n- 【Quantization】Eunhyeok Park, Sungjoo Yoo, Peter Vajda .[Value-aware Quantization for Training and Inference of Neural Networks](https://arxiv.org/pdf/1804.07802) .[J] arXiv preprint arXiv:1804.07802.\n- Liyuan Liu, Xiang Ren, Jingbo Shang, Jian Peng, Jiawei Han .[Efficient Contextualized Representation: Language Model Pruning for  Sequence Labeling](https://arxiv.org/pdf/1804.07827) .[J] arXiv preprint arXiv:1804.07827.\n- Huan Wang, Qiming Zhang, Yuehai Wang, Roland Hu .[Structured Deep Neural Network Pruning by Varying Regularization  Parameters](https://arxiv.org/pdf/1804.09461) .[J] arXiv preprint arXiv:1804.09461.\n- Takashi Shinozaki .[Competitive Learning Enriches Learning Representation and Accelerates  the Fine-tuning of CNNs](https://arxiv.org/pdf/1804.09859) .[J] arXiv preprint arXiv:1804.09859.\n- Hyeong-Ju Kang .[Accelerator-Aware Pruning for Convolutional Neural Networks](https://arxiv.org/pdf/1804.09862) .[J] arXiv preprint arXiv:1804.09862.\n- Chenrui Zhang, Yuxin Peng .[Better and Faster: Knowledge Transfer from Multiple Self-supervised  Learning Tasks via Graph Distillation for Video Classification](https://arxiv.org/pdf/1804.10069) .[J] arXiv preprint arXiv:1804.10069.\n- Chaim Baskin, Eli Schwartz, Evgenii Zheltonozhskii, Natan Liss, Raja Giryes, Alex M. Bronstein, Avi Mendelson .[UNIQ: Uniform Noise Injection for the Quantization of Neural Networks](https://arxiv.org/pdf/1804.10969) .[J] arXiv preprint arXiv:1804.10969.\n- Xuemeng Song, Fuli Feng, Xianjing Han, Xin Yang, Wei Liu, Liqiang Nie .[Neural Compatibility Modeling with Attentive Knowledge Distillation](https://arxiv.org/pdf/1805.00313) .[J] arXiv preprint arXiv:1805.00313.\n- Baohua Sun, Lin Yang, Patrick Dong, Wenhan Zhang, Jason Dong, Charles Young .[Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt  for Mobile and Embedded Applications](https://arxiv.org/pdf/1805.00361) .[J] arXiv preprint arXiv:1805.00361.\n- Biao Zhang, Deyi Xiong, Jinsong Su .[Accelerating Neural Transformer via an Average Attention Network](https://arxiv.org/pdf/1805.00631) .[J] arXiv preprint arXiv:1805.00631.\n- Brian Bartoldson, Adrian Barbu, Gordon Erlebacher .[Enhancing the Regularization Effect of Weight Pruning in Artificial  Neural Networks](https://arxiv.org/pdf/1805.01930) .[J] arXiv preprint arXiv:1805.01930.\n- 【Quantization】","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/chanchichoi%2Fawesome-model-compression/projects"}