目錄

Papers (論文)

1.Introduction and Tutorials (簡介與教程)

2.Transfer Learning Areas and Papers (研究領(lǐng)域與相關(guān)論文)

3.Theory and Survey (理論與綜述)

4.Code (代碼)

5.Transfer Learning Scholars (著名學(xué)者)

6.Transfer Learning Thesis (碩博士論文)

7.Datasets and Benchmarks (數(shù)據(jù)集與評(píng)測(cè)結(jié)果)

8.Transfer Learning Challenges (遷移學(xué)習(xí)比賽)

Journals and Conferences

Applications (遷移學(xué)習(xí)應(yīng)用)

Other Resources (其他資源)

來源?

Papers (論文)

Awesome transfer learning papers (遷移學(xué)習(xí)文章匯總)

• Paperweekly: A website to recommend and read paper notes

Latest papers:

• By topic:?doc/awesome_papers.md
• By date:?doc/awesome_paper_date.md

Updated at 2023-04-27:

• Multi-Source to Multi-Target Decentralized Federated Domain Adaptation [arxiv]

  • Multi-source to multi-target federated domain adaptation 多源多目標(biāo)的聯(lián)邦域自適應(yīng)

• ICML'23 AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation [arxiv]

  • Adaptive test-time adaptation 非參數(shù)化分類器進(jìn)行測(cè)試時(shí)adaptation

Updated at 2023-04-23:

• Improved Test-Time Adaptation for Domain Generalization [arxiv]

  • Improved test-time adaptation for domain generalization

• Reweighted Mixup for Subpopulation Shift [arxiv]

  • Reweighted mixup for subpopulation shift

Updated at 2023-04-18:

• CVPR'23 Zero-shot Generative Model Adaptation via Image-specific Prompt Learning [arxiv]

  • Zero-shot generative model adaptation via image-specific prompt learning 零樣本的生成模型adaptation

• Source-free Domain Adaptation Requires Penalized Diversity [arxiv]

  • Source-free DA requires penalized diversity

• Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation [arxiv]

  • Domain generalization for medical segmentation 用domain generalization進(jìn)行醫(yī)學(xué)分割

• CVPR'23 Meta-causal Learning for Single Domain Generalization [arxiv]

  • Meta-causal learning for domain generalization

• Domain Generalization In Robust Invariant Representation [arxiv]

  • Domain generalization in robust invariant representation

Updated at 2023-04-10:

• Beyond Empirical Risk Minimization: Local Structure Preserving Regularization for Improving Adversarial Robustness [arxiv]

  • Local structure preserving for adversarial robustness 通過保留局部結(jié)構(gòu)來進(jìn)行對(duì)抗魯棒性

• TFS-ViT: Token-Level Feature Stylization for Domain Generalization [arxiv]

  • Token-level feature stylization for domain generalization 用token-level特征變換進(jìn)行domain generalization

• Are Data-driven Explanations Robust against Out-of-distribution Data? [arxiv]

  • Data-driven explanations robust? 探索數(shù)據(jù)驅(qū)動(dòng)的解釋是否是OOD魯棒的

• ERM++: An Improved Baseline for Domain Generalization [arxiv]

  • Improved ERM for domain generalization 提高的ERM用于domain generalization

Updated at 2023-04-04:

• CVPR'23 Feature Alignment and Uniformity for Test Time Adaptation [arxiv]

  • Feature alignment for test-time adaptation 使用特征對(duì)齊進(jìn)行測(cè)試時(shí)adaptation

• Finding Competence Regions in Domain Generalization [arxiv]

  • Finding competence regions in domain generalization 在DG中發(fā)現(xiàn)能力區(qū)域

• CVPR'23 TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [arxiv]

  • Improve generalization and adversarial robustness 同時(shí)提高魯棒性和泛化性

• CVPR'23 Trainable Projected Gradient Method for Robust Fine-tuning [arxiv]

  • Trainable PGD for robust fine-tuning 可訓(xùn)練的pgd用于魯棒的微調(diào)技術(shù)

• Parameter-Efficient Tuning Makes a Good Classification Head [arxiv]

  • Parameter-efficient tuning makes a good classification head 參數(shù)高效的遷移學(xué)習(xí)成就一個(gè)好的分類頭

• Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning [arxiv]

  • Continual domain shift learning using adaptation and generalization 使用 adaptation和DG進(jìn)行持續(xù)分布變化的學(xué)習(xí)

1.Introduction and Tutorials (簡介與教程)

Want to quickly learn transfer learning？想盡快入門遷移學(xué)習(xí)？看下面的教程。

• Books 書籍

  • Introduction to Transfer Learning: Algorithms and Practice?[Buy or read]
  • 《遷移學(xué)習(xí)》（楊強(qiáng)）?[Buy] [English version]
  • 《遷移學(xué)習(xí)導(dǎo)論》(王晉東、陳益強(qiáng)著)?[Homepage] [Buy]

• Blogs 博客

  • Zhihu blogs - 知乎專欄《小王愛遷移》系列文章

• Video tutorials 視頻教程

  • Transfer learning 遷移學(xué)習(xí):
    • Recent advance of transfer learning - 2022年最新遷移學(xué)習(xí)發(fā)展現(xiàn)狀探討
    • Definitions of transfer learning area - 遷移學(xué)習(xí)領(lǐng)域名詞解釋?[Article]
    • Transfer learning by Hung-yi Lee @ NTU - 臺(tái)灣大學(xué)李宏毅的視頻講解(中文視頻)
  • Domain generalization 領(lǐng)域泛化：
    • IJCAI-ECAI'22 tutorial on domain generalization - 領(lǐng)域泛化tutorial
    • Domain generalization - 遷移學(xué)習(xí)新興研究方向領(lǐng)域泛化
  • Domain adaptation 領(lǐng)域自適應(yīng)：
    • Domain adaptation - 遷移學(xué)習(xí)中的領(lǐng)域自適應(yīng)方法(中文)

• Brief introduction and slides 簡介與ppt資料

  • Recent advance of transfer learning
  • Domain generalization survey
  • Brief introduction in Chinese
    • PPT (English)?|?PPT (中文)
  • 遷移學(xué)習(xí)中的領(lǐng)域自適應(yīng)方法 Domain adaptation:?PDF?｜?Video on Bilibili?|?Video on Youtube
  • Tutorial on transfer learning by Qiang Yang:?IJCAI'13?|?2016 version

• Talk is cheap, show me the code 動(dòng)手教程、代碼、數(shù)據(jù)

  • Pytorch tutorial on transfer learning
    • Pytorch finetune
    • DeepDA: a unified deep domain adaptation toolbox
    • DeepDG: a unified deep domain generalization toolbox
    • 更多 More...

• Transfer Learning Scholars and Labs - 遷移學(xué)習(xí)領(lǐng)域的著名學(xué)者、代表工作及實(shí)驗(yàn)室介紹

• Negative transfer - 負(fù)遷移

2.Transfer Learning Areas and Papers (研究領(lǐng)域與相關(guān)論文)

• Survey
• Theory
• Per-training/Finetuning
• Knowledge distillation
• Traditional domain adaptation
• Deep domain adaptation
• Domain generalization
• Source-free domain adaptation
• Multi-source domain adaptation
• Heterogeneous transfer learning
• Online transfer learning
• Zero-shot / few-shot learning
• Multi-task learning
• Transfer reinforcement learning
• Transfer metric learning
• Federated transfer learning
• Lifelong transfer learning
• Safe transfer learning
• Transfer learning applications

3.Theory and Survey (理論與綜述)

Here are some articles on transfer learning theory and survey.

Survey (綜述文章)：

• 2023 Source-Free Unsupervised Domain Adaptation: A Survey [arxiv]
• 2022?Transfer Learning for Future Wireless Networks: A Comprehensive Survey
• 2022?A Review of Deep Transfer Learning and Recent Advancements
• 2022?Transferability in Deep Learning: A Survey, from Mingsheng Long in THU.
• 2021 Domain generalization: IJCAI-21?Generalizing to Unseen Domains: A Survey on Domain Generalization?|?知乎文章?|?微信公眾號(hào)
  • First survey on domain generalization
  • 第一篇對(duì)Domain generalization (領(lǐng)域泛化)的綜述
• 2021 Vision-based activity recognition:?A Survey of Vision-Based Transfer Learning in Human Activity Recognition
• 2021 ICSAI?A State-of-the-Art Survey of Transfer Learning in Structural Health Monitoring
• 2020?Transfer learning: survey and classification, Advances in Intelligent Systems and Computing.
• 2020 遷移學(xué)習(xí)最新survey，來自中科院計(jì)算所莊福振團(tuán)隊(duì)，發(fā)表在Proceedings of the IEEE:?A Comprehensive Survey on Transfer Learning
• 2020 負(fù)遷移的綜述：Overcoming Negative Transfer: A Survey
• 2020 知識(shí)蒸餾的綜述:?Knowledge Distillation: A Survey
• 用transfer learning進(jìn)行sentiment classification的綜述：A Survey of Sentiment Analysis Based on Transfer Learning
• 2019 一篇新survey：Transfer Adaptation Learning: A Decade Survey
• 2018 一篇遷移度量學(xué)習(xí)的綜述:?Transfer Metric Learning: Algorithms, Applications and Outlooks
• 2018 一篇最近的非對(duì)稱情況下的異構(gòu)遷移學(xué)習(xí)綜述：Asymmetric Heterogeneous Transfer Learning: A Survey
• 2018 Neural style transfer的一個(gè)survey：Neural Style Transfer: A Review
• 2018 深度domain adaptation的一個(gè)綜述：Deep Visual Domain Adaptation: A Survey
• 2017 多任務(wù)學(xué)習(xí)的綜述，來自香港科技大學(xué)楊強(qiáng)團(tuán)隊(duì)：A survey on multi-task learning
• 2017 異構(gòu)遷移學(xué)習(xí)的綜述：A survey on heterogeneous transfer learning
• 2017 跨領(lǐng)域數(shù)據(jù)識(shí)別的綜述：Cross-dataset recognition: a survey
• 2016?A survey of transfer learning。其中交代了一些比較經(jīng)典的如同構(gòu)、異構(gòu)等學(xué)習(xí)方法代表性文章。
• 2015 中文綜述：遷移學(xué)習(xí)研究進(jìn)展
• 2010?A survey on transfer learning
• Survey on applications - 應(yīng)用導(dǎo)向的綜述：
  • 視覺domain adaptation綜述：Visual Domain Adaptation: A Survey of Recent Advances
  • 遷移學(xué)習(xí)應(yīng)用于行為識(shí)別綜述：Transfer Learning for Activity Recognition: A Survey
  • 遷移學(xué)習(xí)與增強(qiáng)學(xué)習(xí)：Transfer Learning for Reinforcement Learning Domains: A Survey
  • 多個(gè)源域進(jìn)行遷移的綜述：A Survey of Multi-source Domain Adaptation。

Theory （理論文章）:

• ICML-20?Few-shot domain adaptation by causal mechanism transfer
  • The first work on causal transfer learning
  • 日本理論組大佬Sugiyama的工作，causal transfer learning
• CVPR-19?Characterizing and Avoiding Negative Transfer
  • Characterizing and avoid negative transfer
  • 形式化并提出如何避免負(fù)遷移
• ICML-20?On Learning Language-Invariant Representations for Universal Machine Translation
  • Theory for universal machine translation
  • 對(duì)統(tǒng)一機(jī)器翻譯模型進(jìn)行了理論論證
• NIPS-06?Analysis of Representations for Domain Adaptation
• ML-10?A Theory of Learning from Different Domains
• NIPS-08?Learning Bounds for Domain Adaptation
• COLT-09?Domain adaptation: Learning bounds and algorithms
• MMD paper：A Hilbert Space Embedding for Distributions?and?A Kernel Two-Sample Test
• Multi-kernel MMD paper:?Optimal kernel choice for large-scale two-sample tests

4.Code (代碼)

Unified codebases for:

• Deep domain adaptation
• Deep domain generalization
• See all codes here:?transferlearning/code at master · jindongwang/transferlearning · GitHub.

More: see?HERE?and?HERE?for an instant run using Google's Colab.

5.Transfer Learning Scholars (著名學(xué)者)

Here are some transfer learning scholars and labs.

全部列表以及代表工作性見這里

Please note that this list is far not complete. A full list can be seen in?here. Transfer learning is an active field.?If you are aware of some scholars, please add them here.

6.Transfer Learning Thesis (碩博士論文)

Here are some popular thesis on transfer learning.

這里, 提取碼：txyz。

7.Datasets and Benchmarks (數(shù)據(jù)集與評(píng)測(cè)結(jié)果)

Please see?HERE?for the popular transfer learning?datasets and benchmark?results.

這里整理了常用的公開數(shù)據(jù)集和一些已發(fā)表的文章在這些數(shù)據(jù)集上的實(shí)驗(yàn)結(jié)果。

8.Transfer Learning Challenges (遷移學(xué)習(xí)比賽)

• Visual Domain Adaptation Challenge (VisDA)

Journals and Conferences

See?here?for a full list of related journals and conferences.

Applications (遷移學(xué)習(xí)應(yīng)用)

• Computer vision
• Medical and healthcare
• Natural language processing
• Time series
• Speech
• Multimedia
• Recommendation
• Human activity recognition
• Autonomous driving
• Others

See?HERE?for transfer learning applications.

遷移學(xué)習(xí)應(yīng)用請(qǐng)見這里。

Other Resources (其他資源)

• Call for papers:

  • Advances in Transfer Learning: Theory, Algorithms, and Applications, DDL: October 2021

• Related projects:

  • Salad:?A semi-supervised domain adaptation library

來源?

jindongwang/transferlearning: Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-遷移學(xué)習(xí) (github.com)文章來源地址http://www.zghlxwxcb.cn/news/detail-460542.html

到了這里，關(guān)于【論文合集】Awesome Transfer Learning的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！