迁移学习 材料集合

谁都会走 提交于 2020-12-03 13:11:55

迁移学习 材料集合

目录

迁移学习 材料集合

Book

novel_papers

1) novel_papers on transfer learning

2) novel_papers on related fileds

更多 DA awesome​​​​​​​

入门参考

小结

Excellent Scholars

新论文追踪

科研方法论

Presentation


大部分内容 转自 GitHub:https://github.com/yuntaodu/Transfer-learning-materials

Book

《迁移学习简明手册》

https://github.com/jindongwang/transferlearning-tutorial

 

novel_papers

1) novel_papers on transfer learning

number Title Conference/journel + year Code Keywords Benenit for us
54 Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID (paper) NIPS 2020 code contrastive learning, DA, Re-ID contrastive learning + DA
53 Measuring Information Transfer in Neural Networks (paper) arvix 2020     maybe useful for DA
52 Open-Set Hypothesis Transfer with Semantic Consistency (paper) arvix 2020   source free, open set  
51 Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling (paper) ICML 2020   stein discrepancy a new metric that is never used in DA
50 Impact of ImageNet Model Selection on Domain Adaptation(paper) WACV 2020 workshop   shallow methods with different deep features 实验结果很迷惑
49 Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks(paper) arvix 2020   pretraining good papers
48 Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation (paper) ECCV 2020 code SSDA, intar-domain discrepancy good questions
47 Measuring Information Transfer in Neural Networks(paper)       interesting paper
46 Neural transfer learning for natural language processing(paper) 2019 PDH thesis   NLP, transfer lerning very detailed related work
45 When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasets(paper)     SSL, TL, experiments many results related to multiple SSL methods can be seen in this paper
44 Unsupervised Transfer Learning for Spatiotemporal Predictive Networks (paper) ICML 2020      
43 Estimating Generalization under Distribution Shifts via Domain-Invariant Representations (paper) ICML 2020 code new theory recommend to read
42 Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation (paper) ICML 2020 code ideas from theory recommend to read
41 LEEP: A New Measure to Evaluate Transferability of Learned Representations (paper) ICML 2020   new metric for transferability easy to use for other tasks
40 Label-Noise Robust Domain Adaptation ICML2020     the author is a rising star
39 Progressive Graph Learning for Open-Set Domain Adaptation (paper) ICML 2020 code open set DA  
38 Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation (paper) ICML 2020 code source-free DA recommend to read, new trneds
37 Graph Optimal Transport for Cross-Domain Alignment (paper) ICML 2020   graph for DA connenction with GCN
36 Learning Deep Kernels for Non-Parametric Two-Sample Tests (paper) ICML 2020 code extend MMD to deep  
35 Adversarial-Learned Loss for Domain Adaptation AAAI 2020   noisy label, adversarial learning  
34 Transfer Learning for Anomaly Detection through Localized and Unsupervised Instance Selection AAAI 2020   transfer learning, anamaly detection  
33 Dynamic Instance Normalization for Arbitrary Style Transfer AAAI 2020   dynamic instance normalization  
32 AdaFilter: Adaptive Filter Fine-Tuning for Deep Transfer Learning AAAI 2020   gated output, fine-tune  
31 Bi-Directional Generation for Unsupervised Domain Adaptation AAAI 2020   differert feature extractor, different classifiers connection with ICML 2019, the third term
30 Discriminative Adversarial Domain Adaptation AAAI 2020   discriminative information with adversarial learning  
29 Domain Generalization Using a Mixture of Multiple Latent Domains AAAI 2020      
28 Multi-Source Distilling Domain Adaptation AAAI 2020   multi-source  
27 Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision CVPR 2020 code Entropy adversarial based  
26 Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective CVPR 2020   long-tailed  
25 Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering CVPR 2020 code cluster  
24 Stochastic Classifiers for Unsupervised Domain Adaptation CVPR 2020   stochastic two classifiers simialer to MCD
23 Progressive Adversarial Networks for Fine-Grained Domain Adaptation CVPR 2020   fine-grained similar to mutil-aspect opinion analysis
22 Model Adaptation: Unsupervised Domain Adaptation without Source Data CVPR 2020     Recommend to read, new problems
21 Towards Inheritable Models for Open-Set Domain Adaptation CVPR 2020 code    
20 Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification ECCV 2020      
19 Extending and Analyzing Self-Supervised Learning Across Domains (paper) ECCV 2020      
18 Dual Mixup Regularized Learning for Adversarial Domain Adaptation (paper) ECCV 2020      
17 Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation (paper ECCV 2020 code SSL reguralization, Anchors new methods, good writings
16 Do Adversarially Robust ImageNet Models Transfer Better? arvix 2020 code Many experiments  
15 Visualizing Transfer Learning arvix 2020   interesting  
14 A SURVEY ON DOMAIN ADAPTATION THEORY:LEARNING BOUNDS AND THEORETICAL GUARANTEES (paper) arvix 2020   theory  
13 SpotTune: Transfer Learning through Adaptive Fine-tuning (paper) CVPR 2019 code   dynamic routing is a general method
12 Parameter Transfer Unit for Deep Neural Networks (paper) PAKDD 2019 best paper     good idea, recommened to read
11 Heterogeneous Domain Adaptation via Soft Transfer Network (paper) ACM MM 2019      
10 Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation (paper) ICML 2012      
9 Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification (paper) arvix 2020     Good ideas
8 Towards Recognizing Unseen Categories in Unseen Domains (paper) arvix 2020     new problems
7 MiCo: Mixup Co-Training for Semi-Supervised Domain Adaptation (paper) arvix 2020     good framework
6 Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning (paper arvix 2020      
5 Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation (paper) ACM MM 2020 code    
4 Learning from a Complementary-label Source Domain: Theory and Algorithms(paper) arvix 2020 code   novel idea
3 Class-Incremental Domain Adaptation(paper) ECCV 2020     new problems
2 Class-incremental Learning via Deep Model Consolidation (paper) WACV 2020      
1 Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition (paper) ACM MM 2020     similar idea with us
0 A Review of Single-Source Deep Unsupervised Visual Domain Adaptation paper arvix 2020   Review a good review! It contains many results of the state-of-the-art method

2) novel_papers on related fileds

number Title Conference/journel + year Code Keywords Benenit for us
14 Self-Loop Uncertainty: A Novel Pseudo-Label for Semi-Supervised Medical Image Segmentation (paper) MICCAI 2020   ssl, pseudo label  
13 Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning (paper) NIPS 2020   semi-supervised, weight smaples it can be used in our work
12 Safe semi-supervised learning: a brief introduction (paper)     safe ssl new concept, maybe useful for negative transfer
11 Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data (paper) ICML 2020 code ssl, unseen class open set, maybe useful for negative transfer
10 (RECORD: Resource Constrained Semi-Supervised Learning under Distribution Shifpaper) KDD 2020   online, distribution shift maybe useful for negative transfer
9 Adversarial Examples Improve Image Recognition (paper) CVPR 2020   Adversarial examples, image recognition, batch normalization Same idea can be explored in DA
8 Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning AAAI 2020   unsupervised learning, semi-supervised learning  
7 Self-supervised Label Augmentation via Input Transformations ICML 2020 code self-supervised ideas can be used to many tasks
6 Learning with Multiple Complementary Labels (paper) ICML 2020      
5 Deep Divergence Learning (paper) ICML 2020   divergence  
4 Confidence-Aware Learning for Deep Neural Networks (paper) ICML 2020 code confidence  
3 Continual Learning in Human Activity Recognition:an Empirical Analysis of Regularization (paper) ICML workshop code Continual learning bechmark  
2 Automated Phrase Mining from Massive Text Corpora (paper)        
1 Adversarially-Trained Deep Nets Transfer Better(paper arvix 2020     new findings
0 Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation arvix (paper)     same ideas with us

 

 

 

更多 DA awesome​​​​​​​

【必看】https://github.com/jindongwang/transferlearning

https://github.com/zhaoxin94/awesome-domain-adaptation#distance-based-methods

https://github.com/barebell/DA

 

入门参考

本部分内容适合初学者,将一些本领域中的经典论文按照时间线进行分类、梳理,分为浅层域适应、深度域适应、对抗域适应和域适应领域四部分。

针对每一部分,列举了3-4篇经典论文,建议详读这些经典论文,泛读这些经典论文的后续论文,并对其中的部分算法进行实现。

预期学习时间为2-3个月, 详细计划安排见入门参考

围绕这些论文,曾有一个相应的讨论班,相关的日程和资料如下:

小结

  • 迁移学习理论 pptpdf
  • Online Transfer Learning pdf

Excellent Scholars

新论文追踪

科研方法论

Presentation

  • 龙明盛 CCDM 2020 视频 , ppt
  • VALSE Webinar 20-19期 迁移学习 (个人非常推荐, 对新手不友好,对进阶有帮助,质量很高!) 视频报告简介
  • 龙明盛_NJU2019 Transfer Learning Theories and Algorithms ppt
  • 龙明盛 Valse 2019 Transfer Learning_From Algorithms to Theories and Back 视频 ppt
  • 游凯超 智源论坛 2019 领域适配前沿研究--场景、方法与模型选择 视频,ppt
  • 王玫 2019 deep_domain_adaptation 视频ppt
  • 吴恩达 NIPS 2016 Nuts and bolts of building AI applications using Deep Learning 视频(需科学上网),ppt
易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!