Awesome-Multi-Task-Learning
An up-to-date list of works on Multi-Task Learning
https://github.com/WeiHongLee/Awesome-Multi-Task-Learning
Last synced: about 12 hours ago
JSON representation
-
Benchmarks & Code
-
Image Classification
- CelebA
- Meta-dataset - research/meta-dataset)]
- Visual Domain Decathlon
- CelebA
- CelebA
- CelebA
- CelebA
- CelebA
- CelebA
- CelebA
- CelebA
- CelebA
- CelebA
- CelebA
- CelebA
- [TorchJD - objective optimization (focusing on gradient combination) of pytorch models.
- [Multi-Task-Transformer - task Learning including dense prediction problems and 3D detection on Cityscapes.
- [Multi-Task-Learning-PyTorch - task Dense Prediction.
- [Auto-λ - task Dense Prediction, Robotics.
- [UniversalRepresentations - task Dense Prediction](https://github.com/VICO-UoE/UniversalRepresentations/tree/main/DensePred) (including different loss weighting strategies), [Multi-domain Classification](https://github.com/VICO-UoE/UniversalRepresentations/tree/main/VisualDecathlon), [Cross-domain Few-shot Learning](https://github.com/VICO-UoE/URL).
- [MTAN - task Dense Prediction, Multi-domain Classification.
- [ASTMT - task Dense Prediction.
- [LibMTL - task Dense Prediction.
- [MTPSL - task Partially-supervised Learning for Dense Prediction.
- [Resisual Adapater - domain Classification.
-
Dense Prediction Tasks
- NYUv2
- Cityscapes - dataset.com/)]
- PASCAL-Context - context/)]
- KITTI
- SUN RGB-D
- BDD100K - data.berkeley.edu/)]
- [dataset and code
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Cityscapes - dataset.com/)]
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Taskonomy
- Cityscapes - dataset.com/)]
- SUN RGB-D
- Cityscapes - dataset.com/)]
- SUN RGB-D
- SUN RGB-D
- Omnidata
-
-
Papers
-
2016 and earlier
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- Cross-Stitch - stitch-Networks-for-Multi-task-Learning)]
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
-
2022
- TSA - UoE/URL)]
- [paper
- [paper
- Auto-λ - lambda)]
- [paper
- [paper - Group/M3ViT)]
- [paper
- [paper - with-Category-Shifts)]
- [paper
- [paper
- Universal Representations - UoE/UniversalRepresentations)]
- [paper
- [paper
- [paper
- InvPT
- MultiMAE
- [paper
- [paper
- [paper
- [paper - task-oriented_generative_modeling)]
- [paper - mtl)]
- [paper
- Gato
- MTPSL - UoE/MTPSL)]
- OMNIVORE
- [paper
- [paper - labs.com/~mas/DYMU/)]
- SHIFT
- [paper - Labs/DiSparse-Multitask-Model-Compression)]
- MulT
- [paper
- [paper
- [paper - research/google-research/tree/master/muNet)]
- [paper
- [paper
- [paper - RL/AdaRL-code)]
- [paper - parameter-efficient-tuning)]
- Rotograd
- [paper
- [paper
- [paper
- [paper
- MultiMAE
- InvPT
- [paper
- TSA - UoE/URL)]
- [paper
- [paper
- [paper - with-Category-Shifts)]
- Universal Representations - UoE/UniversalRepresentations)]
- Auto-λ - lambda)]
- Gato
- OMNIVORE
- [paper
- [paper - labs.com/~mas/DYMU/)]
- [paper
-
2024
- [paper
- [paper - research/BayesAgg_MTL)]
- [paper
- [paper - UoE/MTPSL)]
- [paper
- [paper
- [paper - park.github.io/DTR/)]
- [paper
- [paper - CVPR-2024)]
- [paper
- [paper
- [paper - Lab/fairgrad)]
- [paper
- [paper - Research/MTMamba)]
- [paper
- [paper - CVPR-2024)]
- [paper - lab/MTLoRA)]
- [paper - zero/FedHCA2)]
- [paper
- [paper
- [paper
- [paper - research/BayesAgg_MTL)]
- [paper
-
2023
- [paper
- [paper - research/deeplab2)]
- [paper
- [paper
- [paper
- [paper - UoE/MTPSL)]
- [paper
- [paper
- [paper
- [paper - Model-Selector)]
- [paper
- [paper - research/google-research/tree/master/moe_mtl)]
- [paper
- [paper - based-MTL)]
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper - jku/L2M)]
- InvPT++ - Task-Transformer/tree/main/InvPT)]
- [paper - XIX/FAMO)]
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper - www.cs.umass.edu/mod-squad/)]
- [paper - lu/etr-nlp-mtl)]
- [paper
- [paper
- [paper - Task-Transformer/tree/main/TaskPrompter)] [[dataset](https://arxiv.org/pdf/2304.00971.pdf)]
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper - vision/DenseMTL)]
- [paper - research/deeplab2)]
- [paper
- [paper
- [paper - Lab/sdmgrad)]
- [paper
- [paper - lu/etr-nlp-mtl)]
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- InvPT++ - Task-Transformer/tree/main/InvPT)]
- [paper - XIX/FAMO)]
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper - www.cs.umass.edu/mod-squad/)]
- [paper
-
2021
- [paper
- [paper
- CAGrad - XIX/CAGrad)]
- [paper
- [paper
- [paper
- [paper - VILAB/XDEnsembles)]
- [paper
- URL - UoE/URL)]
- tri-M - M-ICCV)]
- [paper
- [paper
- [paper
- FLUTE - research/meta-dataset)]
- [paper - uda)]
- [paper - tasking)]
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper - MTL)]
- Gradient Vaccine
- IMTL
- [paper
- URT
- [paper
- [paper - weighting)]
- [paper
- FLUTE - research/meta-dataset)]
- [paper
- [paper
- [paper
- [paper
- [paper
-
2020
- [paper - Module)]
- [paper
- [paper
- [paper
- [paper
- [paper - repo/duality-diagram-similarity)]
- KD4MTL - UoE/KD4MTL)]
- [paper
- [paper - VILAB/XTConsistency)]
- paper - multi-task)]
- [paper
- [paper
- [paper
- [paper - gfx/ContinuousParetoMTL)]
- [paper
- [paper
- paper
- [paper
- [paper
- [paper
- [paper
- [paper
- paper
- paper
- paper
- paper
- paper
- paper
- KD4MTL - UoE/KD4MTL)]
- paper
- [paper
- [paper
- GradDrop
- [paper
- [paper - gfx/ContinuousParetoMTL)]
- [paper
- [paper
-
2019
- [paper
- [paper - L/ParetoMTL)]
- [paper
- [paper
- [paper
- [paper - snu/Deep-Elastic-Network)]
- [paper - task-architecture-search)]
- [paper
- [paper - research/google-research/tree/master/bam)]
- [paper - CNN)]
- [paper
- [paper - CVPR19-release)]
- Geometric Loss Strategy (GLS)
- [paper - n-Pals)]
- [paper
- [paper
- [paper
- [paper
- [paper - networks)]
- [paper - research/google-research/tree/master/bam)]
- [paper - Paper.pdf)]
-
2018
-
2017
-
2025
-
-
Survey & Study
-
Workshops
-
2016 and earlier
- Universal Representations for Computer Vision Workshop at BMVC 2022
- Workshop on Multi-Task Learning in Computer Vision (DeepMTL) at ICCV 2021
- Adaptive and Multitask Learning: Algorithms & Systems Workshop (AMTL) at ICML 2019
- Workshop on Multi-Task and Lifelong Reinforcement Learning at ICML 2015
- Transfer and Multi-Task Learning: Trends and New Perspectives at NeurIPS 2015
- Second Workshop on Transfer and Multi-task Learning at NeurIPS 2014
- New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks Workshop at NeurIPS 2013
- Second Workshop on Transfer and Multi-task Learning at NeurIPS 2014
- New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks Workshop at NeurIPS 2013
- Second Workshop on Transfer and Multi-task Learning at NeurIPS 2014
- New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks Workshop at NeurIPS 2013
- Second Workshop on Transfer and Multi-task Learning at NeurIPS 2014
- New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks Workshop at NeurIPS 2013
-
-
Online Courses
-
2016 and earlier
-
Programming Languages
Sub Categories
Keywords
multi-task-learning
6
pytorch
4
python
2
multitask-learning
2
multiobjective-optimization
2
multi-objective-optimization
2
deep-learning
2
computer-vision
1
eccv2020
1
nyud
1
pascal
1
scene-understanding
1
segmentation
1
partially-supervised
1
semi-supervised-learning
1
auxiliary-learning
1
meta-learning
1
attention-model
1
mmoe
1
mtl
1
multi-domain-learning
1
ple
1
jacobian-descent
1
optimization
1
torch
1