awesome-edge-intelligence-collections
About DNN compression and acceleration on Edge Devices.
https://github.com/fangvv/awesome-edge-intelligence-collections
Last synced: 12 days ago
JSON representation
-
Paper
-
- Local Binary Convolutional Neural Networks
- Quantize weights and activations in Recurrent Neural Networks
- The ZipML Framework for Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning
- Quantized Convolutional Neural Networks for Mobile Devices
- Loss-aware Binarization of Deep Networks
- Towards the Limit of Network Quantization
- Deep Learning with Low Precision by Half-wave Gaussian Quantization
- ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks
- Trained Ternary Quantization
- Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization
- Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- A Survey of Model Compression and Acceleration for Deep Neural Networks
- Dynamic Capacity Networks
- ResNeXt: Aggregated Residual Transformations for Deep Neural Networks
- Residual Attention Network for Image Classification
- SEP-Nets: Small and Effective Pattern Networks
- Deep Networks with Stochastic Depth
- Learning Infinite Layer Networks Without the Kernel Trick
- Coordinating Filters for Faster Deep Neural Networks
- Squeezedet: Unified, small, low power fully convolutional neural networks
- Soft Weight-Sharing for Neural Network Compression
- Learning both Weights and Connections for Efficient Neural Networks
- Dynamic Network Surgery for Efficient DNNs
- ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA
- Faster CNNs with Direct Sparse Convolutions and Guided Pruning
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
- Efficient and Accurate Approximations of Nonlinear Convolutional Networks
- Accelerating Very Deep Convolutional Networks for Classification and Detection
- Convolutional neural networks with low-rank regularization
- A Survey of Model Compression and Acceleration for Deep Neural Networks
- Dynamic Capacity Networks
- ResNeXt: Aggregated Residual Transformations for Deep Neural Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Residual Attention Network for Image Classification
- SEP-Nets: Small and Effective Pattern Networks
- Deep Networks with Stochastic Depth
- Learning Infinite Layer Networks Without the Kernel Trick
- Coordinating Filters for Faster Deep Neural Networks
- Efficient and Accurate Approximations of Nonlinear Convolutional Networks
- Xception: Deep Learning with Depthwise Separable Convolutions
- Efficient Sparse-Winograd Convolutional Neural Networks
- Model compression as constrained optimization, with application to neural nets. Part I: general framework
- Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
- Squeezedet: Unified, small, low power fully convolutional neural networks
- Model compression as constrained optimization, with application to neural nets. Part II: quantization
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
- ResBinNet: Residual Binary Neural Network
- DSD: Dense-Sparse-Dense Training for Deep Neural Networks
-
Quantization
-
Survey
-
Model and structure
- NasNet: Learning Transferable Architectures for Scalable Image Recognition
- DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices
- CondenseNet: An Efficient DenseNet using Learned Group Convolutions
- Shift-based Primitives for Efficient Convolutional Neural Networks
- Shift-based Primitives for Efficient Convolutional Neural Networks
-
Pruning
- To prune, or not to prune: exploring the efficacy of pruning for model compression
- Learning Structured Sparsity in Deep Neural Networks
- Scalpel: Customizing DNN Pruning to the Underlying Hardware Parallelism
- RePr: Improved Training of Convolutional Filters
- Channel Pruning for Accelerating Very Deep Neural Networks
- Learning Efficient Convolutional Networks through Network Slimming
- NISP: Pruning Networks using Neuron Importance Score Propagation
- Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
- MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
- “Learning-Compression” Algorithms for Neural Net Pruning
- Data-Driven Sparse Structure Selection for Deep Neural Networks
-
Low-rank Approximation
-
System
- DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications
- DeepEye: Resource Efficient Local Execution of Multiple Deep Vision Models using Wearable Commodity Hardware
- MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU
- DeepSense: A GPU-based deep convolutional neural network framework on commodity mobile devices
- DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
- EIE: Efficient Inference Engine on Compressed Deep Neural Network
- MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints
- DXTK: Enabling Resource-efficient Deep Learning on Mobile and Embedded Devices with the DeepX Toolkit
- Sparsification and Separation of Deep Learning Layers for Constrained Resource Inference on Wearables
- CNNdroid: GPU-Accelerated Execution of Trained Deep Convolutional Neural Networks on Android
- fpgaConvNet: A Toolflow for Mapping Diverse Convolutional Neural Networks on Embedded FPGAs
- An Early Resource Characterization of Deep Learning on Wearables, Smartphones and Internet-of-Things Devices - App ’15]
-
References
- Reading List
- Reading List 3
- An Introduction to different Types of Convolutions in Deep Learning
- CNN中千奇百怪的卷积方式大汇总
- link
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- 纵览轻量化卷积神经网络：SqueezeNet、MobileNet、ShuffleNet、Xception
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
- An Introduction to different Types of Convolutions in Deep Learning
-
Knowledge Distillation
- Net2net: Accelerating learning via knowledge transfer
- A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learnin
- DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
- Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy
- Moonshine: Distilling with Cheap Convolutions
- Deep Model Compression: Distilling Knowledge from Noisy Teachers
- Data-Free Knowledge Distillation For Deep Neural Networks
- Model compression via distillation and quantization
-
Miscellaneous
-
Distilling
-
Binarized Neural Network
-
-
Papers
-
Pruning
- Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing
- Channel pruning for accelerating very deep neural networks
- Faster CNNs with Direct Sparse Convolutions and Guided Pruning
- Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization
- Data-Driven Sparse Structure Selection for Deep Neural Networks
- ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA
- AMC: AutoML for model compression and acceleration on mobile devices
- Pruning Filters for Efficient ConvNets
- Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- Soft Weight-Sharing for Neural Network Compression
- Learning both Weights and Connections for Efficient Neural Networks
- Dynamic Network Surgery for Efficient DNNs
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
-
Low Rank Approximation
- Speeding up convolutional neural networks with low rank expansions
- Accelerating Very Deep Convolutional Networks for Classification and Detection
- Convolutional neural networks with low-rank regularization
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- Efficient and Accurate Approximations of Nonlinear Convolutional Networks
- Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
-
Distillation
- MobileID: Face Model Compression by Distilling Knowledge from Neurons
- Learning Efficient Object Detection Models with Knowledge Distillation
- Deep Model Compression: Distilling Knowledge from Noisy Teachers
- Data-Free Knowledge Distillation For Deep Neural Networks
- Knowledge Projection for Effective Design of Thinner and Faster Deep Neural Networks
- Moonshine: Distilling with Cheap Convolutions
- Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification
- Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
- Sequence-Level Knowledge Distillation
- Learning Loss for Knowledge Distillation with Conditional Adversarial Networks
- DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
- FitNets: Hints for Thin Deep Nets
- Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
- Dark knowledge
- Distilling the Knowledge in a Neural Network
-
Architecture
- Xception: Deep Learning with Depthwise Separable Convolutions
- MobileNetV2: Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation
- AddressNet: Shift-based Primitives for Efficient Convolutional Neural Networks
- ResNeXt: Aggregated Residual Transformations for Deep Neural Networks
- Residual Attention Network for Image Classification
- Squeezedet: Unified, small, low power fully convolutional neural networks
- SEP-Nets: Small and Effective Pattern Networks
- Dynamic Capacity Networks
- Learning Infinite Layer Networks Without the Kernel Trick
- Coordinating Filters for Faster Deep Neural Networks
- Deep Networks with Stochastic Depth
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
-
Quantization
- Trained Ternary Quantization
- Quantize weights and activations in Recurrent Neural Networks
- Fixed-Point Performance Analysis of Recurrent Neural Networks
- Loss-aware Binarization of Deep Networks
- Quantized Convolutional Neural Networks for Mobile Devices
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- The ZipML Framework for Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning
- Compressing Deep Convolutional Networks using Vector Quantization
- Towards the Limit of Network Quantization
- Deep Learning with Low Precision by Half-wave Gaussian Quantization
- ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks
-
Binarization
- Binarized Convolutional Neural Networks with Separable Filters for Efficient Hardware Acceleration
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- Local Binary Convolutional Neural Networks
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
-
General
-
-
**Network Compression**
-
**Sparsity regularizers & Pruning**
-
-
**Hardware Accelerator**
-
**Benchmark and Platform Analysis**
-
**Convolutional Neural Networks**
-
-
**Conference Papers**
-
Articles
-
Videos
-
Training & tutorials
-
-
Quantization
-
Pruning
-
Knowledge Distallation
-
Network Architecture
-
Matrix Factorization(Low-rank Approximation)
Categories
Sub Categories
References
50
Training & tutorials
45
Pruning
25
Distillation
15
Quantization
15
System
12
Architecture
12
Knowledge Distillation
8
Model and structure
6
Low Rank Approximation
6
Binarization
5
Distilling
4
**NIPS 2018**
3
Miscellaneous
3
Binarized Neural Network
2
Assorted
2
**Benchmark and Platform Analysis**
2
Survey
2
Low-rank Approximation
2
Howtos
1
Blogs
1
**Sparsity regularizers & Pruning**
1
General
1
**CVPR 2019**
1
**Convolutional Neural Networks**
1