{"id":4682,"url":"https://github.com/SimonVandenhende/Awesome-Multi-Task-Learning","name":"Awesome-Multi-Task-Learning","description":"A list of multi-task learning papers and projects. ","projects_count":80,"last_synced_at":"2026-07-21T16:00:35.679Z","repository":{"id":45269353,"uuid":"289860892","full_name":"SimonVandenhende/Awesome-Multi-Task-Learning","owner":"SimonVandenhende","description":"A list of multi-task learning papers and projects. ","archived":false,"fork":false,"pushed_at":"2022-01-31T17:47:22.000Z","size":276,"stargazers_count":386,"open_issues_count":1,"forks_count":49,"subscribers_count":15,"default_branch":"master","last_synced_at":"2026-06-15T12:18:13.064Z","etag":null,"topics":["computer-vision","machine-learning","multitask-learning","research"],"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/SimonVandenhende.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}},"created_at":"2020-08-24T07:41:31.000Z","updated_at":"2026-04-30T02:08:59.000Z","dependencies_parsed_at":"2022-08-12T11:51:09.349Z","dependency_job_id":null,"html_url":"https://github.com/SimonVandenhende/Awesome-Multi-Task-Learning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SimonVandenhende/Awesome-Multi-Task-Learning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimonVandenhende%2FAwesome-Multi-Task-Learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimonVandenhende%2FAwesome-Multi-Task-Learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimonVandenhende%2FAwesome-Multi-Task-Learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimonVandenhende%2FAwesome-Multi-Task-Learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SimonVandenhende","download_url":"https://codeload.github.com/SimonVandenhende/Awesome-Multi-Task-Learning/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimonVandenhende%2FAwesome-Multi-Task-Learning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35069183,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-03T02:00:05.635Z","response_time":110,"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":"2024-01-06T20:25:01.533Z","updated_at":"2026-07-21T16:00:35.680Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Datasets","Architectures","Neural Architecture Search","Optimization strategies","Transfer learning \u0026 Domain Adaptation","Workshop","Survey papers","Robustness","Other"],"sub_categories":["Other","Encoder-based architectures","Decoder-based architectures"],"readme":"# Awesome Multi-Task Learning\nThis page contains a list of papers on multi-task learning for computer vision. \nPlease create a pull request if you wish to add anything. \nIf you are interested, consider reading our recent survey paper.\n\n\u003e [**Multi-Task Learning for Dense Prediction Tasks: A Survey**](https://arxiv.org/abs/2004.13379)\n\u003e\n\u003e [Simon Vandenhende](https://twitter.com/svandenh1), [Stamatios Georgoulis](https://twitter.com/stam_g), Wouter Van Gansbeke, Marc Proesmans, Dengxin Dai and Luc Van Gool.\n\n\n## Workshop\n\n:loudspeaker: :loudspeaker: :loudspeaker: We organized a **workshop** on multi-task learning at ICCV 2021 ([Link](https://sites.google.com/view/deepmtlworkshop/home)).\n\n- Jan 13: The recordings of our invited talks are now available on [Youtube](https://youtube.com/playlist?list=PLJwr5SeuN6XMXbWxnzwD1e7n-aOOJpWJn).\n\n## Table of Contents:\n\n- [Survey papers](#survey) \n- [Datasets](#datasets)\n- [Architectures](#architectures)\n  - [Encoder-based](#encoder)\n  - [Decoder-based](#decoder)\n  - [Other](#otherarchitectures)\n- [Neural Architecture Search](#nas)\n- [Optimization strategies](#optimization)\n- [Transfer learning](#transfer)\n\n\n\u003ca name=\"survey\"\u003e\u003c/a\u003e\n## Survey papers\n- \u003ca name=\"vandenhende2020revisiting\"\u003e\u003c/a\u003e Vandenhende, S., Georgoulis, S., Van Gansbeke, W., Proesmans, M., Dai, D., \u0026 Van Gool, L. \n*[Multi-Task Learning for Dense Prediction Tasks: A Survey](https://ieeexplore.ieee.org/abstract/document/9336293)*,\nT-PAMI, 2020. [[PyTorch](https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch)]\n\n- \u003ca name=\"ruder2017survey\"\u003e\u003c/a\u003e Ruder, S. \n*[An overview of multi-task learning in deep neural networks](https://arxiv.org/abs/1706.05098)*,\nArXiv, 2017. \n\n- \u003ca name=\"zhang2017survey\"\u003e\u003c/a\u003e Zhang, Y.\n*[A survey on multi-task learning](https://arxiv.org/abs/1707.08114)*, \nArXiv, 2017.\n\n- \u003ca name=\"gong2019comparison\"\u003e\u003c/a\u003e Gong, T., Lee, T., Stephenson, C., Renduchintala, V., Padhy, S., Ndirango, A., ... \u0026 Elibol, O. H. \n*[A comparison of loss weighting strategies for multi task learning in deep neural networks](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8848395)*,\nIEEE Access, 2019. \n\n\n\u003ca name=\"datasets\"\u003e\u003c/a\u003e\n## Datasets\nThe following datasets have been regularly used in the context of multi-task learning:\n\n- [NYUDv2](https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html)\n- [Cityscapes](https://www.cityscapes-dataset.com/)\n- [PASCAL](https://github.com/facebookresearch/astmt)\n- [Taskonomy](https://github.com/StanfordVL/taskonomy)\n- [KITTI](http://www.cvlibs.net/datasets/kitti/)\n- [SUN RGB-D](https://rgbd.cs.princeton.edu/)\n- [BDD100K](https://arxiv.org/pdf/1805.04687.pdf)\n\n\u003ca name=\"architectures\"\u003e\u003c/a\u003e\n## Architectures\n\n\u003ca name=\"encoder\"\u003e\u003c/a\u003e\n### Encoder-based architectures\n\n- \u003ca name=\"misra2016cross\"\u003e\u003c/a\u003e Misra, I., Shrivastava, A., Gupta, A., \u0026 Hebert, M.\n*[Cross-stitch networks for multi-task learning](https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Misra_Cross-Stitch_Networks_for_CVPR_2016_paper.html)*,\nCVPR, 2016. [[PyTorch](https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch)]\n\n- \u003ca name=\"gao2019nddr\"\u003e\u003c/a\u003e Gao, Y., Ma, J., Zhao, M., Liu, W., \u0026 Yuille, A. L. \n*[Nddr-cnn: Layerwise feature fusing in multi-task cnns by neural discriminative dimensionality reduction](https://openaccess.thecvf.com/content_CVPR_2019/html/Gao_NDDR-CNN_Layerwise_Feature_Fusing_in_Multi-Task_CNNs_by_Neural_Discriminative_CVPR_2019_paper.html)*,\nCVPR, 2019. [[Tensorflow](https://github.com/ethanygao/NDDR-CNN)] [[PyTorch](https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch)]\n\n- \u003ca name=\"liu2019mtan\"\u003e\u003c/a\u003e Liu, S., Johns, E., \u0026 Davison, A. J. \n*[End-to-end multi-task learning with attention](https://arxiv.org/abs/1803.10704)*,\nCVPR, 2019. [[PyTorch](https://github.com/lorenmt/mtan)]\n\n\n\u003ca name=\"decoder\"\u003e\u003c/a\u003e\n### Decoder-based architectures\n\n- \u003ca name=\"bilen2016multi\"\u003e\u003c/a\u003e Bilen, H., Vedaldi, A.\n*[Integrated perception with recurrent multi-task neural networks](https://proceedings.neurips.cc/paper/2016/file/06409663226af2f3114485aa4e0a23b4-Paper.pdf)*,\nNeurIPS, 2016.\n\n- \u003ca name=\"xu2018pad\"\u003e\u003c/a\u003e Xu, D., Ouyang, W., Wang, X., \u0026 Sebe, N.\n*[Pad-net: Multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing](https://openaccess.thecvf.com/content_cvpr_2018/html/Xu_PAD-Net_Multi-Tasks_Guided_CVPR_2018_paper.html)*,\nCVPR, 2018.  \n\n- \u003ca name=\"zhang2018jtrl\"\u003e\u003c/a\u003e Zhang, Z., Cui, Z., Xu, C., Jie, Z., Li, X., \u0026 Yang, J.\n*[Joint task-recursive learning for semantic segmentation and depth estimation](https://openaccess.thecvf.com/content_ECCV_2018/html/Zhenyu_Zhang_Joint_Task-Recursive_Learning_ECCV_2018_paper.html)*,\nECCV, 2018.\n\n- \u003ca name=\"ruder2019sluice\"\u003e\u003c/a\u003e Ruder, S., Bingel, J., Augenstein, I., \u0026 Søgaard, A. \n*[Latent multi-task architecture learning](https://www.aaai.org/ojs/index.php/AAAI/article/view/4410)*,\nAAAI, 2019.\n\n- \u003ca name=\"zhang2019papnet\"\u003e\u003c/a\u003e Zhang, Z., Cui, Z., Xu, C., Yan, Y., Sebe, N., \u0026 Yang, J. \n*[Pattern-affinitive propagation across depth, surface normal and semantic segmentation](https://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Pattern-Affinitive_Propagation_Across_Depth_Surface_Normal_and_Semantic_Segmentation_CVPR_2019_paper.html)*,\nCVPR, 2019.\n\n- \u003ca name=\"zhou2020structure\"\u003e\u003c/a\u003e Zhou, L., Cui, Z., Xu, C., Zhang, Z., Wang, C., Zhang, T., \u0026 Yang, J.\n*[Pattern-Structure Diffusion for Multi-Task Learning](https://openaccess.thecvf.com/content_CVPR_2020/html/Zhou_Pattern-Structure_Diffusion_for_Multi-Task_Learning_CVPR_2020_paper.html)*,\nCVPR, 2020.\n\n- \u003ca name=\"vandenhende2020mti\"\u003e\u003c/a\u003e Vandenhende, S., Georgoulis, S., \u0026 Van Gool, L. \n*[MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning](https://arxiv.org/abs/2001.06902)*,\nECCV, 2020. [[PyTorch](https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch)]\n  \n\u003ca name=\"otherarchitectures\"\u003e\u003c/a\u003e\n\n### Other\n\n- \u003ca name=\"yang2016deep\"\u003e\u003c/a\u003e Yang, Y., \u0026 Hospedales, T. \n*[Deep multi-task representation learning: A tensor factorisation approach](https://arxiv.org/abs/1605.06391)*,\nICLR, 2017.\n\n- \u003ca name=\"kokkinos2017uber\"\u003e\u003c/a\u003e Kokkinos, Iasonas.\n*[Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory](https://openaccess.thecvf.com/content_cvpr_2017/html/Kokkinos_Ubernet_Training_a_CVPR_2017_paper.html)*,\nCVPR, 2017.\n\n- \u003ca name=\"rebuffi2017learning\"\u003e\u003c/a\u003e Rebuffi, S. A., Bilen, H., \u0026 Vedaldi, A. \n*[Learning multiple visual domains with residual adapters](https://arxiv.org/abs/1705.08045)*,\nNIPS, 2017.\n\n- \u003ca name=\"long2017multilinear\"\u003e\u003c/a\u003e Long, M., Cao, Z., Wang, J., \u0026 Philip, S. Y. \n*[Learning multiple tasks with multilinear relationship networks](http://papers.nips.cc/paper/6757-learning-multiple-tasks-with-deep-relationship-networks)*,\nNIPS, 2017.\n\n- \u003ca name=\"meyerson2017beyond\"\u003e\u003c/a\u003e Meyerson, E., \u0026 Miikkulainen, R. \n*[Beyond shared hierarchies: Deep multitask learning through soft layer ordering](https://arxiv.org/abs/1711.00108)*,\nICLR, 2018.\n\n- \u003ca name=\"rosenbaum2017routing\"\u003e\u003c/a\u003e Rosenbaum, C., Klinger, T., \u0026 Riemer, M.\n*[Routing networks: Adaptive selection of non-linear functions for multi-task learning](https://arxiv.org/abs/1711.01239)*,\nICLR, 2018.\n\n- \u003ca name=\"mallya2018piggy\"\u003e\u003c/a\u003e Mallya, A., Davis, D., \u0026 Lazebnik, S.\n*[Piggyback: Adapting a single network to multiple tasks by learning to mask weights](https://openaccess.thecvf.com/content_ECCV_2018/html/Arun_Mallya_Piggyback_Adapting_a_ECCV_2018_paper.html)*,\nECCV, 2018.\n\n- \u003ca name=\"rebuffi2018efficient\"\u003e\u003c/a\u003e Rebuffi, S. A., Bilen, H., \u0026 Vedaldi, A.\n*[Efficient parametrization of multi-domain deep neural networks](https://arxiv.org/abs/1803.10082)*,\nCVPR, 2018.\n\n- \u003ca name=\"maninis2019astmt\"\u003e\u003c/a\u003e Maninis, K. K., Radosavovic, I., \u0026 Kokkinos, I. \n*[Attentive single-tasking of multiple tasks](https://arxiv.org/abs/1904.08918)*,\nCVPR, 2019. [[PyTorch](https://github.com/facebookresearch/astmt)]\n\n- \u003ca name=\"kanakis2020reparameterizing\"\u003e\u003c/a\u003e Kanakis, M., Bruggemann, D., Saha, S., Georgoulis, S., Obukhov, A., \u0026 Van Gool, L.\n*[Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference](https://arxiv.org/abs/2007.12540)*,\nECCV, 2020.\n\n- \u003ca name=\"wang2020multi\"\u003e\u003c/a\u003e Wang, Q., Ke, J., Greaves, J., Chu, G., Bender, G., Sbaiz, L., Go, A., Howard, A., Yang, F., Yang, M.H. \u0026 Gilbert, J.\n*[Multi-path Neural Networks for On-device Multi-domain Visual Classification](https://arxiv.org/pdf/2010.04904.pdf)*,\nWACV, 2021.\n\n- \u003ca name=\"bruggemann2021exploring\"\u003e\u003c/a\u003e Bruggemann, D., Kanakis, M., Obukhov, A., Georgoulis, S., \u0026 Van Gool, L. *[Exploring Relational Context for Multi-Task Dense Prediction](https://arxiv.org/abs/2104.13874)*, ArXiv, 2021.\n\n- \u003ca name=\"li2021universal\"\u003e\u003c/a\u003e Li, W. H., Liu, X., \u0026 Bilen, H. *[Universal Representation Learning from Multiple Domains for Few-shot Classification](https://openaccess.thecvf.com/content/ICCV2021/papers/Li_Universal_Representation_Learning_From_Multiple_Domains_for_Few-Shot_Classification_ICCV_2021_paper.pdf)*, ICCV, 2021.\n\n- \u003ca name=\"li2021learning\"\u003e\u003c/a\u003e Li, W. H., Liu, X., \u0026 Bilen, H. *[Learning Multiple Dense Prediction Tasks from Partially Annotated Data](https://arxiv.org/pdf/2111.14893.pdf)*, ArXiv, 2021.\n\n\u003ca name=\"nas\"\u003e\u003c/a\u003e\n## Neural Architecture Search\n\n- \u003ca name=\"lu2017fully\"\u003e\u003c/a\u003e Lu, Y., Kumar, A., Zhai, S., Cheng, Y., Javidi, T., \u0026 Feris, R.\n*[Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification](https://openaccess.thecvf.com/content_cvpr_2017/html/Lu_Fully-Adaptive_Feature_Sharing_CVPR_2017_paper.html)*,\nCVPR, 2017. \n\n- \u003ca name=\"bragman2019stochastic\"\u003e\u003c/a\u003e Bragman, F. J., Tanno, R., Ourselin, S., Alexander, D. C., \u0026 Cardoso, J.\n*[Stochastic filter groups for multi-task cnns: Learning specialist and generalist convolution kernels](https://openaccess.thecvf.com/content_ICCV_2019/html/Bragman_Stochastic_Filter_Groups_for_Multi-Task_CNNs_Learning_Specialist_and_Generalist_ICCV_2019_paper.html)*,\nICCV, 2019.\n\n- \u003ca name=\"newell2019feature\"\u003e\u003c/a\u003e Newell, A., Jiang, L., Wang, C., Li, L. J., \u0026 Deng, J. \n*[Feature partitioning for efficient multi-task architectures](https://arxiv.org/abs/1908.04339)*,\n ArXiv, 2019.\n\n- \u003ca name=\"guo2020learning\"\u003e\u003c/a\u003e Guo, P., Lee, C. Y., \u0026 Ulbricht, D. \n*[Learning to Branch for Multi-Task Learning](https://proceedings.icml.cc/static/paper_files/icml/2020/5057-Paper.pdf)*, \nICML, 2020. \n\n- \u003ca name=\"standley2019tasks\"\u003e\u003c/a\u003e Standley, T., Zamir, A. R., Chen, D., Guibas, L., Malik, J., \u0026 Savarese, S. \n*[Which Tasks Should Be Learned Together in Multi-task Learning?](https://arxiv.org/pdf/1905.07553.pdf)*,\nICML, 2020.\n\n- \u003ca name=\"vandenhende2019branched\"\u003e\u003c/a\u003e Vandenhende, S., Georgoulis, S., De Brabandere, B., \u0026 Van Gool, L. \n*[Branched multi-task networks: deciding what layers to share](https://arxiv.org/abs/1904.02920)*, \nBMVC, 2020. \n\n- \u003ca name=\"bruggeman2020auomated\"\u003e\u003c/a\u003e Bruggemann, D., Kanakis, M., Georgoulis, S., \u0026 Van Gool, L.\n*[Automated Search for Resource-Efficient Branched Multi-Task Networks](https://arxiv.org/abs/2008.10292)*,\nBMVC, 2020.\n\n- \u003ca name=\"sun2019adashare\"\u003e\u003c/a\u003e Sun, X., Panda, R., \u0026 Feris, R. \n*[AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning](https://arxiv.org/abs/1911.12423)*,\nNIPS, 2020.\n\n\u003ca name=\"optimization\"\u003e\u003c/a\u003e\n## Optimization strategies\n\n- \u003ca name=\"kendall2018uncertainty\"\u003e\u003c/a\u003e Kendall, A., Gal, Y., \u0026 Cipolla, R. \n*[Multi-task learning using uncertainty to weigh losses for scene geometry and semantics](https://openaccess.thecvf.com/content_cvpr_2018/html/Kendall_Multi-Task_Learning_Using_CVPR_2018_paper.html)*,\nCVPR, 2018. \n\n- \u003ca name=\"zhao2018modulation\"\u003e\u003c/a\u003e Zhao, X., Li, H., Shen, X., Liang, X., \u0026 Wu, Y. \n*[A modulation module for multi-task learning with applications in image retrieval](https://openaccess.thecvf.com/content_ECCV_2018/html/Xiangyun_Zhao_A_Modulation_Module_ECCV_2018_paper.html)*,\nECCV, 2018.\n\n- \u003ca name=\"chen2018gradnorm\"\u003e\u003c/a\u003e Chen, Z., Badrinarayanan, V., Lee, C. Y., \u0026 Rabinovich, A. \n*[Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks](http://proceedings.mlr.press/v80/chen18a.html)*,\nICML, 2018.\n\n- \u003ca name=\"sener2018mgda\"\u003e\u003c/a\u003e Sener, O., \u0026 Koltun, V. \n*[Multi-task learning as multi-objective optimization](http://papers.nips.cc/paper/7334-multi-task-learning-as-multi-objective-optimization)*,\nNIPS, 2018. [[PyTorch](https://github.com/intel-isl/MultiObjectiveOptimization)]\n\n- \u003ca name=\"liu2017adversarial\"\u003e\u003c/a\u003e Liu, P., Qiu, X., \u0026 Huang, X.\n*[Adversarial multi-task learning for text classification](https://www.aclweb.org/anthology/P17-1001.pdf)*,\nACL, 2018.\n\n- \u003ca name=\"guo2018dynamic\"\u003e\u003c/a\u003e Guo, M., Haque, A., Huang, D. A., Yeung, S., \u0026 Fei-Fei, L.\n*[Dynamic task prioritization for multitask learning](https://openaccess.thecvf.com/content_ECCV_2018/html/Michelle_Guo_Focus_on_the_ECCV_2018_paper.html)*,\nECCV, 2018. \n\n- \u003ca name=\"lin2019pareto\"\u003e\u003c/a\u003e Lin, X., Zhen, H. L., Li, Z., Zhang, Q. F., \u0026 Kwong, S.\n*[Pareto multi-task learning](https://papers.nips.cc/paper/9374-pareto-multi-task-learning)*,\nNIPS, 2019.\n\n- \u003ca name=\"suteu2019orthogonal\"\u003e\u003c/a\u003e Suteu, M., \u0026 Guo, Y. \n*[Regularizing Deep Multi-Task Networks using Orthogonal Gradients](https://arxiv.org/abs/1912.06844)*,\nArXiv, 2019. \n\n- \u003ca name=\"yu2020surgery\"\u003e\u003c/a\u003e Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., \u0026 Finn, C. \n*[Gradient surgery for multi-task learning](https://arxiv.org/abs/2001.06782)*,\nNIPS, 2020. [[Tensorflow](https://github.com/tianheyu927/PCGrad)]\n\n- \u003ca name=\"chen2020sign\"\u003e\u003c/a\u003e Chen, Z., Ngiam, J., Huang, Y., Luong, T., Kretzschmar, H., Chai, Y., \u0026 Anguelov, D. \n*[Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout](https://arxiv.org/pdf/2010.06808.pdf)*,\nNIPS, 2020.\n\n- \u003ca name=\"li2020knowledge\"\u003e\u003c/a\u003e Li, W. H., \u0026 Bilen, H. \n*[Knowledge Distillation for Multi-task Learning](https://arxiv.org/pdf/2007.06889.pdf)*,\nECCV-Workshop, 2020. [[PyTorch](https://github.com/WeiHongLee/KD-MTL)]\n\n- \u003ca name=\"borse2021inverseform\"\u003e\u003c/a\u003e Borse, S., Wang, Y., Zhang, Y., \u0026 Porikli, F. *[InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://openaccess.thecvf.com/content/CVPR2021/papers/Borse_InverseForm_A_Loss_Function_for_Structured_Boundary-Aware_Segmentation_CVPR_2021_paper.pdf)*, CVPR 2021.\n\n- \u003ca name=\"vasu2021instance\"\u003e\u003c/a\u003e Vasu P., Saxena S., Tuzel O. *[Instance-Level Task Parameters: A Robust Multi-task Weighting Framework](https://arxiv.org/pdf/2106.06129.pdf)*, ArXiv, 2021.    \n     \n     \n\u003ca name=\"transfer\"\u003e\u003c/a\u003e\n## Transfer learning \u0026 Domain Adaptation\n\n- \u003ca name=\"cui2018large\"\u003e\u003c/a\u003e Cui, Y., Song, Y., Sun, C., Howard, A., \u0026 Belongie, S.\n*[Large scale fine-grained categorization and domain-specific transfer learning](https://openaccess.thecvf.com/content_cvpr_2018/html/Cui_Large_Scale_Fine-Grained_CVPR_2018_paper.html)*,\nCVPR, 2018.\n\n- \u003ca name=\"zamir2018taskonomy\"\u003e\u003c/a\u003e Zamir, A. R., Sax, A., Shen, W., Guibas, L. J., Malik, J., \u0026 Savarese, S.\n*[Taskonomy: Disentangling task transfer learning](https://openaccess.thecvf.com/content_cvpr_2018/html/Zamir_Taskonomy_Disentangling_Task_CVPR_2018_paper.html)*,\nCVPR, 2018. [[PyTorch](https://github.com/StanfordVL/taskonomy)]\n\n- \u003ca name=\"achille2019task2vec\"\u003e\u003c/a\u003e Achille, A., Lam, M., Tewari, R., Ravichandran, A., Maji, S., Fowlkes, C. C., ... \u0026 Perona, P.\n*[Task2vec: Task embedding for meta-learning](https://openaccess.thecvf.com/content_ICCV_2019/html/Achille_Task2Vec_Task_Embedding_for_Meta-Learning_ICCV_2019_paper.html)*,\nICCV, 2019. [[PyTorch](https://github.com/awslabs/aws-cv-task2vec)]\n\n- \u003ca name=\"dwivedi2019rsa\"\u003e\u003c/a\u003e Dwivedi, K., \u0026 Roig, G.\n*[Representation similarity analysis for efficient task taxonomy \u0026 transfer learning](https://openaccess.thecvf.com/content_CVPR_2019/html/Dwivedi_Representation_Similarity_Analysis_for_Efficient_Task_Taxonomy__Transfer_Learning_CVPR_2019_paper.html)*,\nCVPR, 2019. [[PyTorch](https://github.com/kshitijd20/RSA-CVPR19-release)]\n\n- \u003ca name=\"saha2021learning\"\u003e\u003c/a\u003e Saha, S., Obukhov, A., Paudel, D. P., Kanakis, M., Chen, Y., Georgoulis, S., \u0026 Van Gool, L. *[Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation](https://openaccess.thecvf.com/content/CVPR2021/papers/Saha_Learning_To_Relate_Depth_and_Semantics_for_Unsupervised_Domain_Adaptation_CVPR_2021_paper.pdf)*, CVPR, 2021.\n\n\u003ca name=\"robustness\"\u003e\u003c/a\u003e\n## Robustness\n- \u003ca name=\"maomultitask2020\"\u003e\u003c/a\u003e Mao, C., Gupta, A., Nitin, V., Ray, B., Song, S., Yang, J., \u0026 Vondrick, C.\n*[Multitask Learning Strengthens Adversarial Robustness](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123470154.pdf)*,\nECCV, 2020. [[PyTorch](https://github.com/columbia/MTRobust)]\n\n- \u003ca name=\"zamirrobust2020\"\u003e\u003c/a\u003e Zamir, A. R., Sax, A., Cheerla, N., Suri, R., Cao, Z., Malik, J., \u0026 Guibas, L. J. \n*[Robust Learning Through Cross-Task Consistency](https://openaccess.thecvf.com/content_CVPR_2020/html/Zamir_Robust_Learning_Through_Cross-Task_Consistency_CVPR_2020_paper.html)*,\nCVPR, 2020. \n\n- \u003ca name=\"georgescu2020anomaly\"\u003e\u003c/a\u003e Georgescu, M. I., Barbalau, A., Ionescu, R. T., Khan, F. S., Popescu, M., \u0026 Shah, M. *[Anomaly Detection in Video via Self-Supervised and Multi-Task Learning](https://openaccess.thecvf.com/content/CVPR2021/papers/Georgescu_Anomaly_Detection_in_Video_via_Self-Supervised_and_Multi-Task_Learning_CVPR_2021_paper.pdf)*, CVPR, 2021.\n\n\u003ca name=\"other\"\u003e\u003c/a\u003e\n## Other\n- \u003ca name=\"steerable\"\u003e\u003c/a\u003e Eftekhar, A.,Sax, A., Malik, J., Zamir, A. *[Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets From 3D Scans](https://openaccess.thecvf.com/content/ICCV2021/html/Eftekhar_Omnidata_A_Scalable_Pipeline_for_Making_Multi-Task_Mid-Level_Vision_Datasets_ICCV_2021_paper.html)*, ICCV, 2021.\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/simonvandenhende%2Fawesome-multi-task-learning/projects"}