https://github.com/bachi55/transferlearning

Everything about Transfer Learning and Domain Adaptation--迁移学习

https://github.com/bachi55/transferlearning

Repository

Everything about Transfer Learning and Domain Adaptation--迁移学习

https://github.com/bachi55/transferlearning/blob/master/

#  Transfer Learning  

[![Awesome](https://awesome.re/badge.svg)](https://awesome.re) [![MIT License](https://img.shields.io/badge/license-MIT-green.svg)](https://opensource.org/licenses/MIT)
[![LICENSE](https://img.shields.io/badge/license-Anti%20996-blue.svg)](https://github.com/996icu/996.ICU/blob/master/LICENSE) [![996.icu](https://img.shields.io/badge/link-996.icu-red.svg)](https://996.icu)


Everything about Transfer Learning (Probably the **most complete** repository?). *Your contribution is highly valued!* If you find this repo helpful, please cite it as follows:

(****) **  

```
@Misc{transferlearning.xyz,
howpublished = {\url{http://transferlearning.xyz}},   
title = {Everything about Transfer Learning and Domain Adapation},  
author = {Wang, Jindong and others}  
}  
```


    

        
Contents
    
    

        
0.Latest Publications ()
        
1.Introduction and Tutorials ()
    
    

        
2.Transfer Learning Areas and Papers ()
        
3.Theory and Survey ()
    
    

        
4.Code ()
        
5.Transfer Learning Scholars ()
    
    

        
6.Transfer Learning Thesis ()
        
7.Datasets and Benchmarks ()
    
    

        
8.Transfer Learning Challenges ()
        
Applications ()
    
    

        
Other Resources ()
        
Contributing ()
    


> [](https://github.com/jindongwang/activityrecognition)[](https://github.com/jindongwang/MachineLearning)

- - -

**NOTE:** You can directly open the code in Gihub Codespaces on the web to run them without downloading! See this figure:

![](png/codespace.png)

![](png/codespace22.png)

## 0.Latest Publications ()

**A good website to see the latest arXiv preprints by search: [Transfer learning](http://arxitics.com/search?q=transfer%20learning&sort=updated#1904.01376/abstract), [Domain adaptation](http://arxitics.com/search?q=domain%20adaptation&sort=updated)**

**arXiv: [Transfer learning](http://arxitics.com/search?q=transfer%20learning&sort=updated#1904.01376/abstract), [Domain adaptation](http://arxitics.com/search?q=domain%20adaptation&sort=updated)**

[ Awesome transfer learning papers](https://github.com/jindongwang/transferlearning/tree/master/doc/awesome_paper.md)

- **Latest papers**

  - 20210319 [Learning Invariant Representations across Domains and Tasks](https://arxiv.org/abs/2103.05114)
    - Automatically learn to match distributions
    - 

  - 20210319 [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://arxiv.org/abs/2103.03097) | [](https://zhuanlan.zhihu.com/p/354740610) | [](https://mp.weixin.qq.com/s/DsoVDYqLB1N7gj9X5UnYqw)
    - First survey on domain generalization
    - Domain generalization ()

  - 20210319 [Cross-domain Activity Recognition via Substructural Optimal Transport](https://arxiv.org/abs/2102.03353) | [](https://zhuanlan.zhihu.com/p/356904023) | [](https://mp.weixin.qq.com/s/QuVrqnPruHgfolYltI1Peg)
    - Using sub-structures for domain adaptation
    - domain adaptation5

[** More...**](https://github.com/jindongwang/transferlearning/tree/master/doc/awesome_paper.md)

- - -

## 1.Introduction and Tutorials ()

Want to quickly learn transfer learning

- The first transfer learning tutorial  
	- [**Transfer Learning Tutorial**](https://zhuanlan.zhihu.com/p/35352154) [Read online](https://tutorial.transferlearning.xyz/), [PDF](http://jd92.wang/assets/files/transfer_learning_tutorial_wjd.pdf)
	- [Zhihu blogs - ](https://zhuanlan.zhihu.com/p/130244395)

- Video tutorials  
	- [Domain adaptation - ()](https://www.bilibili.com/video/BV1T7411R75a/)
    - [Transfer learning by Hung-yi Lee @ NTU - ()](https://www.youtube.com/watch?v=qD6iD4TFsdQ)
	- [Chelsea finn's Stanford CS330 class on multi-task and meta-learning - 2020CS330](https://www.bilibili.com/video/av91772677?p=12)

- Brief introduction and slides ppt
	- [Brief introduction in Chinese](https://github.com/jindongwang/transferlearning/blob/master/doc/%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0%E7%AE%80%E4%BB%8B.md)
	- [PPT (English)](http://jd92.wang/assets/files/l03_transferlearning.pdf) | [PPT ()](http://jd92.wang/assets/files/l08_tl_zh.pdf)
	-  Domain adaptation: [PDF](http://jd92.wang/assets/files/l12_da.pdf)  [Video on Bilibili](https://www.bilibili.com/video/BV1T7411R75a/) | [Video on Youtube](https://www.youtube.com/watch?v=RbIsHNtluwQ&t=22s)
	- Tutorial on transfer learning by Qiang Yang: [IJCAI'13](http://ijcai13.org/files/tutorial_slides/td2.pdf) | [2016 version](http://kddchina.org/file/IntroTL2016.pdf)

- Talk is cheap, show me the code  
  - [Pytorch](https://pytorch.org/tutorials/beginner/transfer_learning_tutorial.html)
	- [Pytorchfinetune Fine-tune based on Alexnet and Resnet](https://github.com/jindongwang/transferlearning/tree/master/code/AlexNet_ResNet)
	- [Pytorch](https://github.com/jindongwang/transferlearning/tree/master/code/feature_extractor)
	- [ More...](https://github.com/jindongwang/transferlearning/tree/master/code)

- [Transfer Learning Scholars and Labs - ](https://github.com/jindongwang/transferlearning/blob/master/doc/scholar_TL.md)

- [Negative transfer - ](https://www.zhihu.com/question/66492194/answer/242870418)

- - -

## 2.Transfer Learning Areas and Papers ()

Related articles by research areas:

- [General Transfer Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#general-transfer-learning-%E6%99%AE%E9%80%9A%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0)
  - [Theory ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#theory-%E7%90%86%E8%AE%BA)
  - [Others ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#others-%E5%85%B6%E4%BB%96)
- [Domain Adaptation ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#domain-adaptation-%E9%A2%86%E5%9F%9F%E8%87%AA%E9%80%82%E5%BA%94)
  - [Traditional Methods ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#traditional-methods-%E4%BC%A0%E7%BB%9F%E8%BF%81%E7%A7%BB%E6%96%B9%E6%B3%95)
  - [Deep / Adversarial Methods (/)](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#deep--adversarial-methods-%E6%B7%B1%E5%BA%A6%E5%AF%B9%E6%8A%97%E8%BF%81%E7%A7%BB%E6%96%B9%E6%B3%95)
- [Domain Generalization](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#domain-generalization)
- [Multi-source Transfer Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#multi-source-transfer-learning-%E5%A4%9A%E6%BA%90%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0)
- [Heterogeneous Transfer Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#heterogeneous-transfer-learning-%E5%BC%82%E6%9E%84%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0)
- [Online Transfer Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#online-transfer-learning-%E5%9C%A8%E7%BA%BF%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0)
- [Zero-shot / Few-shot Learning](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#zero-shot--few-shot-learning)
- [Deep Transfer Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#deep-transfer-learning-%E6%B7%B1%E5%BA%A6%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0)
  - [Non-Adversarial Transfer Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#non-adversarial-transfer-learning-%E9%9D%9E%E5%AF%B9%E6%8A%97%E6%B7%B1%E5%BA%A6%E8%BF%81%E7%A7%BB)
  - [Deep Adversarial Transfer Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#deep-adversarial-transfer-learning-%E5%AF%B9%E6%8A%97%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0)
- [Multi-task Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#multi-task-learning-%E5%A4%9A%E4%BB%BB%E5%8A%A1%E5%AD%A6%E4%B9%A0)
- [Transfer Reinforcement Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#transfer-reinforcement-learning-%E5%BC%BA%E5%8C%96%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0)
- [Transfer Metric Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#transfer-metric-learning-%E8%BF%81%E7%A7%BB%E5%BA%A6%E9%87%8F%E5%AD%A6%E4%B9%A0)
- [Transitive Transfer Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#transitive-transfer-learning-%E4%BC%A0%E9%80%92%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0)
- [Lifelong Learning ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#lifelong-learning-%E7%BB%88%E8%BA%AB%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0)
- [Negative Transfer ()](https://github.com/jindongwang/transferlearning/blob/master/doc/awesome_paper.md#negative-transfer-%E8%B4%9F%E8%BF%81%E7%A7%BB)
- [Transfer Learning Applications ()](https://github.com/jindongwang/transferlearning/blob/master/doc/transfer_learning_application.md)

[Paperweekly](http://www.paperweekly.site/collections/231/papers): 

- - -

## 3.Theory and Survey ()

Here are some articles on transfer learning theory and survey.

**Survey ()**

- The most influential survey on transfer learning : [A survey on transfer learning](http://ieeexplore.ieee.org/abstract/document/5288526/).

- Latest survey - 
    - 2021 [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://arxiv.org/abs/2103.03097) | [](https://zhuanlan.zhihu.com/p/354740610) | [](https://mp.weixin.qq.com/s/DsoVDYqLB1N7gj9X5UnYqw)
      - First survey on domain generalization
      - Domain generalization ()
    - 2020 surveyProceedings of the IEEE: [A Comprehensive Survey on Transfer Learning](https://arxiv.org/abs/1911.02685)
    - 2020 [Overcoming Negative Transfer: A Survey](https://arxiv.org/abs/2009.00909)
	- 2020 : [Knowledge Distillation: A Survey](https://arxiv.org/abs/2006.05525)
    - transfer learningsentiment classification[A Survey of Sentiment Analysis Based on Transfer Learning](https://ieeexplore.ieee.org/abstract/document/8746210) 
	- 2019 survey[Transfer Adaptation Learning: A Decade Survey](https://arxiv.org/abs/1903.04687)
	- 2018 : [Transfer Metric Learning: Algorithms, Applications and Outlooks](https://arxiv.org/abs/1810.03944)
	- 2018 [Asymmetric Heterogeneous Transfer Learning: A Survey](https://arxiv.org/abs/1804.10834)
	- 2018 Neural style transfersurvey[Neural Style Transfer: A Review](https://arxiv.org/abs/1705.04058)
	- 2018 domain adaptation[Deep Visual Domain Adaptation: A Survey](https://www.sciencedirect.com/science/article/pii/S0925231218306684)
	- 2017 [A survey on multi-task learning](https://arxiv.org/abs/1707.08114)
	- 2017 [A survey on heterogeneous transfer learning](https://link.springer.com/article/10.1186/s40537-017-0089-0)
	- 2017 [Cross-dataset recognition: a survey](https://arxiv.org/abs/1705.04396)
	- 2016 [A survey of transfer learning](https://pan.baidu.com/s/1gfgXLXT)
	- 2015 [](https://pan.baidu.com/s/1bpautob)

- Survey on applications - 
	- domain adaptation[Visual Domain Adaptation: A Survey of Recent Advances](https://pan.baidu.com/s/1o8BR7Vc)
	- [Transfer Learning for Activity Recognition: A Survey](https://pan.baidu.com/s/1kVABOYr)
	- [Transfer Learning for Reinforcement Learning Domains: A Survey](https://pan.baidu.com/s/1slfr0w1)
	- [A Survey of Multi-source Domain Adaptation](https://pan.baidu.com/s/1eSGREF4)

**Theory :**

- Early transfer learning theory papers - 
  - NIPS-06 [Analysis of Representations for Domain Adaptation](https://dl.acm.org/citation.cfm?id=2976474)
  - ML-10 [A Theory of Learning from Different Domains](https://link.springer.com/article/10.1007/s10994-009-5152-4)
  - NIPS-08 [Learning Bounds for Domain Adaptation](http://papers.nips.cc/paper/3212-learning-bounds-for-domain-adaptation)
  - COLT-09 [Domain adaptation: Learning bounds and algorithms](https://arxiv.org/abs/0902.3430)

- Latest theory papers
  - ICML-20 [Few-shot domain adaptation by causal mechanism transfer](https://arxiv.org/pdf/2002.03497.pdf)
  	- The first work on causal transfer learning
  	- Sugiyamacausal transfer learning

  - CVPR-19 [Characterizing and Avoiding Negative Transfer](https://arxiv.org/abs/1811.09751)
  	- Characterizing and avoid negative transfer
  	- 
  - ICML-20 [On Learning Language-Invariant Representations for Universal Machine Translation](https://arxiv.org/abs/2008.04510)
    - Theory for universal machine translation
    - 


- MMD (Maximum mean discrepancy):
  - MMD[A Hilbert Space Embedding for Distributions](https://link.springer.com/chapter/10.1007/978-3-540-75225-7_5)  [A Kernel Two-Sample Test](http://www.jmlr.org/papers/v13/gretton12a.html)
  - MMD(MK-MMD)[Optimal kernel choice for large-scale two-sample tests](http://papers.nips.cc/paper/4727-optimal-kernel-choice-for-large-scale-two-sample-tests)
  - MMDMMD[Matlab](https://github.com/lopezpaz/classifier_tests/tree/master/code/unit_test_mmd) | [Python](https://github.com/jindongwang/transferlearning/tree/master/code/basic/mmd.py)

_ _ _

## 4.Code ()

[](https://github.com/jindongwang/transferlearning/tree/master/code) | Please see [HERE](https://github.com/jindongwang/transferlearning/tree/master/code) for some popular transfer learning codes.

See [HERE](https://colab.research.google.com/drive/1MVuk95mMg4ecGyUAIG94vedF81HtWQAr?usp=sharing) for an instant run using Google's Colab.

_ _ _

## 5.Transfer Learning Scholars ()

Here are some transfer learning scholars and labs.

**[](https://github.com/jindongwang/transferlearning/blob/master/doc/scholar_TL.md)** 

Please note that this list is far not complete. A full list can be seen in [here](https://github.com/jindongwang/transferlearning/blob/master/doc/scholar_TL.md). Transfer learning is an active field. *If you are aware of some scholars, please add them here.*

- General transfer learning algorithms and applications:

  - [Qiang Yang](http://www.cs.ust.hk/~qyang/)IEEE/ACM/AAAI/IAPR/AAAS fellow[[Google scholar](https://scholar.google.com/citations?user=1LxWZLQAAAAJ&hl=zh-CN)]

  - [Sinno Jialin Pan](http://www.ntu.edu.sg/home/sinnopan/)A survey on transfer learningQiang Yang[[Google scholar](https://scholar.google.com/citations?user=P6WcnfkAAAAJ&hl=zh-CN)]

- Transfer learning algorithms:

  - [Wenyuan Dai](https://scholar.google.com.sg/citations?user=AGR9pP0AAAAJ&hl=zh-CN)CEO[[Google scholar](https://scholar.google.com.hk/citations?hl=zh-CN&user=AGR9pP0AAAAJ)]

  - [Mingsheng Long](http://ise.thss.tsinghua.edu.cn/~mlong/)[[Google scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=mingsheng+long&hl=zh-CN&oi=ao)]

  - [Lixin Duan](http://www.lxduan.info/)[[Google scholar](https://scholar.google.com.hk/citations?user=inRIcS0AAAAJ&hl=zh-CN&oi=ao)]

- Transfer learning + computer vision

  - [Boqing Gong](http://boqinggong.info/index.html)AI Lab()[[Google scholar](https://scholar.google.com/citations?user=lv9ZeVUAAAAJ&hl=en)]
  
  - [Tatiana Tommasi](http://tatianatommasi.wixsite.com/tatianatommasi/3)Researcher at the Italian Institute of Technology.

  - [Vinod K Kurmi](https://github.com/vinodkkurmi)[[home page](https://github.com/vinodkkurmi)]: Researcher at the Indian Institute of Technology Kanpur(India)

- Transfer learning + recommendation systems

  - [Weike Pan](https://sites.google.com/site/weikep/) [[Google Scholar](https://scholar.google.com/citations?user=pC5Q26MAAAAJ&hl=en)]

  - [Fuzhen Zhuang](http://www.intsci.ac.cn/users/zhuangfuzhen/)[[Google scholar](https://scholar.google.com/citations?user=klJBYrAAAAAJ&hl=zh-CN&oi=ao)]

- Online transfer learning:

  - [Qingyao Wu](https://sites.google.com/site/qysite/)[[Google scholar](https://scholar.google.com.hk/citations?user=n6e_2IgAAAAJ&hl=zh-CN&oi=ao)]

- Theory:

  - [Tongliang Liu](http://ieeexplore.ieee.org/abstract/document/8259375/)[[Google scholar](https://scholar.google.com.hk/citations?hl=zh-CN&user=EiLdZ_YAAAAJ)]

_ _ _

## 6.Transfer Learning Thesis ()

Here are some popular thesis on transfer learning.



- 2016 Baochen Sun[Correlation Alignment for Domain Adaptation](http://www.cs.uml.edu/~bsun/papers/baochen_phd_thesis.pdf)

- 2015 Boqing Gong[Kernel Methods for Unsupervised Domain Adaptation](https://pan.baidu.com/s/1bpbawv9)

- 2014 [](http://ise.thss.tsinghua.edu.cn/~mlong/doc/phd-thesis-mingsheng-long.pdf)

- 2014 [](https://pan.baidu.com/s/1kVqYXnh)

- 2012 Hao Hu[Learning based Activity Recognition](https://pan.baidu.com/s/1bp2K9HX)

- 2012 Wencheng Zheng[Learning with Limited Data in Sensor-based Human Behavior Prediction](https://pan.baidu.com/s/1o8MbbBk)

- 2010 Sinno Jialin Pan[Feature-based Transfer Learning and Its Applications](https://pan.baidu.com/s/1bUqMfW)

- 2009 [](https://pan.baidu.com/s/1i4Vyygd)

[](https://pan.baidu.com/s/1bqXEASn)

- - -

## 7.Datasets and Benchmarks ()

Please see [HERE](https://github.com/jindongwang/transferlearning/blob/master/data) for the popular transfer learning **datasets and benchmark** results.

[](https://github.com/jindongwang/transferlearning/blob/master/data)

- - -

## 8.Transfer Learning Challenges ()

- [Visual Domain Adaptation Challenge (VisDA)](http://ai.bu.edu/visda-2018/)

- - -

## Applications ()

See [HERE](https://github.com/jindongwang/transferlearning/blob/master/doc/transfer_learning_application.md) for transfer learning applications.

[](https://github.com/jindongwang/transferlearning/blob/master/doc/transfer_learning_application.md)

- - -

## Other Resources ()

- Call for papers:
  - DLKT: [Deep Learning for Knowledge Transfer @ ICDM 2020](http://icdm2020.bigke.org/)

- Related projects:
  - Salad: [A semi-supervised domain adaptation library](https://domainadaptation.org)
  - Dassl: [A PyTorch toolbox for domain adaptation and semi-supervised learning](https://github.com/KaiyangZhou/Dassl.pytorch)

- - -

## Contributing ()

If you are interested in contributing, please refer to [HERE](https://github.com/jindongwang/transferlearning/blob/master/CONTRIBUTING.md) for instructions in contribution.

- - -

### Copyright notice

> ***[Notes]This Github repo can be used by following the corresponding licenses. I want to emphasis that it may contain some PDFs or thesis, which were downloaded by me and can only be used for academic purposes. The copyrights of these materials are owned by corresponding publishers or organizations. All this are for better adademic research. If any of the authors or publishers have concerns, please contact me to delete or replace them.***

> ***[]***

Owner

GitHub Events