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:
关于迁移学习的所有资料,包括:介绍、综述文章、最新文章、代表工作及其代码、常用数据集、硕博士论文、比赛等等。(可能是目前最全的迁移学习资料库?) 欢迎一起贡献! 如果认为本仓库有用,请在你的论文和其他出版物中进行引用!
@Misc{transferlearning.xyz,
howpublished = {\url{http://transferlearning.xyz}},
title = {Everything about Transfer Learning and Domain Adapation},
author = {Wang, Jindong and others}
}
- 迁移学习 Transfer Learning
- 0.Latest Publications (最新论文)
- 1.Introduction and Tutorials (简介与教程)
- 2.Transfer Learning Areas and Papers (研究领域与相关论文)
- 3.Theory and Survey (理论与综述)
- 4.Code (代码)
- 5.Transfer Learning Scholars (著名学者)
- 6.Transfer Learning Thesis (硕博士论文)
- 7.Datasets and Benchmarks (数据集与评测结果)
- 8.Transfer Learning Challenges (迁移学习比赛)
- Applications (迁移学习应用)
- Other Resources (其他资源)
- Contributing (欢迎参与贡献)
A good website to see the latest arXiv preprints by search: Transfer learning, Domain adaptation
一个很好的网站,可以直接看到最新的arXiv文章: Transfer learning, Domain adaptation
迁移学习文章汇总 Awesome transfer learning papers
-
Latest publications
-
20191212 AAAI-20 Transfer value iteration networks
- Transferred value iteration networks
-
20191204 AAAI-20 Online Knowledge Distillation with Diverse Peers
- Online Knowledge Distillation with Diverse Peers
-
20191125 AAAI-20 Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling
- DA with selective pseudo label
- 结构化和选择性的伪标签用于DA
-
20191202 AAAI-20 Towards Oracle Knowledge Distillation with Neural Architecture Search
- Using NAS for knowledge Distillation
- 用NAS帮助知识蒸馏
-
20191202 AAAI-20 Stable Learning via Sample Reweighting
- Theoretical sample reweigting
- 理论和方法,用于sample reweight
-
20191202 PR-19 Correlation-aware Adversarial Domain Adaptation and Generalization
- CORAL and adversarial for adaptation and generalization
- 基于CORAL和对抗网络的DA和DG
-
-
Preprints on arXiv (Not peer-reviewed)
-
20191204 arXiv DeepMimic: Mentor-Student Unlabeled Data Based Training
- Teacher-student training with unlabeled data
- 在大量无标注数据中训练老师-学生网络
-
20191204 arXiv MetAdapt: Meta-Learned Task-Adaptive Architecture for Few-Shot Classification
- Task adaptive structure for few-shot learning
- 目标自适应的结构用于小样本学习
-
20191204 arXiv Data Augmentation for Deep Transfer Learning
- Data Augmentation for Deep Transfer Learning
- 深度学习中进行一些数据增强的实验
-
20191204 arXiv Transferability versus Discriminability: Joint Probability Distribution Adaptation (JPDA)
- Joint adaptation with different weights
- 不同权重的联合概率适配
-
20191125 arXiv Attention Privileged Reinforcement Learning For Domain Transfer
- Attention privileged reinforcement learning for domain transfer
-
20191201 BMVC-19 Domain Adaptation for Object Detection via Style Consistency
- Use style consistency for domain adaptation
- 通过结构一致性来进行domain adaptation
-
-
Preprints on arXiv (Not peer-reviewed)
-
20191202 arXiv Domain-invariant Stereo Matching Networks
- Domain-invariant stereo matching networks
- 领域不变的匹配网络
-
20191202 arXiv Learning Generalizable Representations via Diverse Supervision
- Diverse supervision helps to learn generalizable representations
-
20191202 arXiv AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
- Learning what to share for multi-task learning
- 对多任务学习如何share
-
20191202 arXiv Domain-Aware Dynamic Networks
- Edge devices adaptative computing
- 边缘计算上的自适应计算
-
20191201 arXiv A Transfer Learning Method for Goal Recognition Exploiting Cross-Domain Spatial Features
- A transfer learning method for goal recognition
- 用迁移学习分析语言中的目标
-
-
简介文字资料
- 简单的中文简介 Chinese introduction
- PPT(English)
- PPT(中文)
- 迁移学习中的领域自适应方法 Domain adaptation: PDF | Video
- 清华大学龙明盛老师的深度迁移学习报告 Transfer learning report by Mingsheng Long @ THU:PPT(Samsung)、PPT(Google China)
-
入门教程
-
视频教程
-
动手教程、代码、数据 Hands-on Codes
Related articles by research areas:
- General Transfer Learning (普通迁移学习)
- Domain Adaptation (领域自适应)
- Domain Generalization
- Multi-source Transfer Learning (多源迁移学习)
- Heterogeneous Transfer Learning (异构迁移学习)
- Online Transfer Learning (在线迁移学习)
- Zero-shot / Few-shot Learning
- Deep Transfer Learning (深度迁移学习)
- Multi-task Learning (多任务学习)
- Transfer Reinforcement Learning (强化迁移学习)
- Transfer Metric Learning (迁移度量学习)
- Transitive Transfer Learning (传递迁移学习)
- Lifelong Learning (终身迁移学习)
- Negative Transfer (负迁移)
- Transfer Learning Applications (应用)
Paperweekly: 一个推荐、分享论文的网站比较好,上面会持续整理相关的文章并分享阅读笔记。
Here are some articles on transfer learning theory and survey.
-
迁移学习领域最具代表性的综述是A survey on transfer learning,发表于2010年,对迁移学习进行了比较权威的定义。 -- The most influential survey on transfer learning.
-
迁移学习的理论分析 Transfer Learning Theory:
-
迁移学习方面一直以来都比较缺乏理论分析与证明的文章,以下几篇连贯式的理论文章成为了经典:
-
最近几年在ICML、NIPS、COLT、ALT上出现了一些理论分析的文章,以domain adaptation为关键字可以搜索到。绝大多数都是对上述的扩展和补充。
-
许多研究者在迁移学习的研究中会应用MMD(Maximum Mean Discrepancy)这个最大均值差异来衡量不同domain之间的距离。MMD的理论文章是:
- MMD的提出:A Hilbert Space Embedding for Distributions 以及 A Kernel Two-Sample Test
- 多核MMD(MK-MMD):Optimal kernel choice for large-scale two-sample tests
- MMD及多核MMD代码:Matlab | Python
-
理论研究方面,重点关注Alex Smola、Ben-David、Bernhard Schölkopf、Arthur Gretton等人的研究。
-
-
较新的综述 Latest survey:
- 用transfer learning进行sentiment classification的综述:A Survey of Sentiment Analysis Based on Transfer Learning
- 2019 一篇新survey:Transfer Adaptation Learning: A Decade Survey
- 2018 一篇迁移度量学习的综述: Transfer Metric Learning: Algorithms, Applications and Outlooks
- 2018 一篇最近的非对称情况下的异构迁移学习综述:Asymmetric Heterogeneous Transfer Learning: A Survey
- 2018 Neural style transfer的一个survey:Neural Style Transfer: A Review
- 2018 深度domain adaptation的一个综述:Deep Visual Domain Adaptation: A Survey
- 2017 多任务学习的综述,来自香港科技大学杨强团队:A survey on multi-task learning
- 2017 异构迁移学习的综述:A survey on heterogeneous transfer learning
- 2017 跨领域数据识别的综述:Cross-dataset recognition: a survey
- 2016 A survey of transfer learning。其中交代了一些比较经典的如同构、异构等学习方法代表性文章。
- 2015 中文综述:迁移学习研究进展
-
迁移学习的应用
- 视觉domain adaptation综述:Visual Domain Adaptation: A Survey of Recent Advances
- 迁移学习应用于行为识别综述:Transfer Learning for Activity Recognition: A Survey
- 迁移学习与增强学习:Transfer Learning for Reinforcement Learning Domains: A Survey
- 多个源域进行迁移的综述:A Survey of Multi-source Domain Adaptation。
请见这里 | Please see HERE for some popular transfer learning codes.
Here are some transfer learning scholars and labs.
全部列表以及代表工作性见这里
Please refer to here to see a complete list.
-
Qiang Yang:中文名杨强。香港科技大学计算机系讲座教授,迁移学习领域世界性专家。IEEE/ACM/AAAI/IAPR/AAAS fellow。[Google scholar]
-
Sinno Jialin Pan:杨强的学生,香港科技大学博士,现任新加坡南洋理工大学助理教授。迁移学习领域代表性综述A survey on transfer learning的第一作者(Qiang Yang是二作)。[Google scholar]
-
Wenyuan Dai:中文名戴文渊,上海交通大学硕士,现任第四范式人工智能创业公司CEO。迁移学习领域著名的牛人,在顶级会议上发表多篇高水平文章,每篇论文引用量巨大。[Google scholar]
-
Lixin Duan:中文名段立新,新加坡南洋理工大学博士,现就职于电子科技大学,教授。[Google scholar]
-
Boqing Gong:南加州大学博士,现就职于腾讯AI Lab(西雅图)。曾任中佛罗里达大学助理教授。[Google scholar]
-
Fuzhen Zhuang:中文名庄福振,中科院计算所博士,现任中科院计算所副研究员。[Google scholar]
-
Mingsheng Long:中文名龙明盛,清华大学博士,现任清华大学助理教授、博士生导师。[Google scholar]
-
Qingyao Wu:中文名吴庆耀,现任华南理工大学副教授。主要做在线迁移学习、异构迁移学习方面的研究。[Google scholar]
-
Weike Pan:中文名潘微科,杨强的学生,现任深圳大学副教授,香港科技大学博士毕业。主要做迁移学习在推荐系统方面的一些工作。 [Google Scholar]
-
Tongliang Liu:中文名刘同亮,现任悉尼大学助理教授。主要做迁移学习的一些理论方面的工作。[Google scholar]
-
Tatiana Tommasi:Researcher at the Italian Institute of Technology.
-
Vinod K Kurmi[home page]: Researcher at the Indian Institute of Technology Kanpur(India)
Here are some popular thesis on transfer learning.
硕博士论文可以让我们很快地对迁移学习的相关领域做一些了解,同时,也能很快地了解概括相关研究者的工作。其中,比较有名的有
-
2016 Baochen Sun的Correlation Alignment for Domain Adaptation
-
2015 南加州大学的Boqing Gong的Kernel Methods for Unsupervised Domain Adaptation
-
2014 清华大学龙明盛的迁移学习问题与方法研究
-
2014 中科院计算所赵中堂的自适应行为识别中的迁移学习方法研究
-
2012 杨强的学生Hao Hu的Learning based Activity Recognition
-
2012 杨强的学生Wencheng Zheng的Learning with Limited Data in Sensor-based Human Behavior Prediction
-
2010 杨强的学生Sinno Jialin Pan的Feature-based Transfer Learning and Its Applications
-
2009 上海交通大学戴文渊的基于实例和特征的迁移学习算法研究
其他的文章,请见完整版。
Please see HERE for the popular transfer learning datasets and certain benchmark results.
这里整理了常用的公开数据集和一些已发表的文章在这些数据集上的实验结果。
一些关于迁移学习的国际比赛。
See HERE for transfer learning applications.
迁移学习应用请见这里。
Call for papers about transfer learning:
Related projects:
If you are interested in contributing, please refer to HERE for instructions in contribution.
[文章版权声明]这个仓库是我开源到Github上的,可以遵守相关的开源协议进行使用。这个仓库中包含有很多研究者的论文、硕博士论文等,都来源于在网上的下载,仅作为学术研究使用。我对其中一些文章都写了自己的浅见,希望能很好地帮助理解。这些文章的版权属于相应的出版社。如果作者或出版社有异议,请联系我进行删除。一切都是为了更好地学术!