Materials for transfer learning 中文版, English version
update: Continue to update sice 2023
- (2021,9,13) 新增25篇ICCV 2021 paper
- (2021,7,1) 新增1篇ACL 2021 paper (recommended)
- (2021,7,1) 新增1篇DASFAA 2021 paper
- (2021,6,26) 新增14篇VisDA 2021竞赛
- (2021,6,18) 新增14篇IJCAI 2021 papers、两个Presentation(valse, eccv 2020 tutorial)
- (2021,6,14) 更新14篇ICLR 2021 papers
- (2021,6,9) 新增17篇ICML 2021 papers
- (2021,6,5) 新增51篇 CVPR 2021 papers
- (2021,3,5) 新增video DA papers
- (2021,3,3) 新增1个video DA contest (Domain Adaptation for Action Recognition)
- (2021,2,25）新增 2个 CVPR 2020 workshop and 1个 ICML 2020 workshop
- (2021,2,7）新增 3个 DA papers
- (2021,1,14）新增 ICLR 2021 papers
- (2021,1,7）新增2个 DA paper
- (2020,12,14）新增7个 continous DA paper
- (2020,12,10）新增1个DA paper
- (2020,12,5）新增4个DA paper
- (2020,11,25）新增5个DA paper
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理论四部分。
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
迁移学习竞赛
- VisDA 2017 in ICCV 2017
- VisDA 2018 in ECCV 2018
- VisDA 2019 in ICCV 2019
- VisDA 2020 in ECCV 2020
- Video DA in CVPR 2021
- VisDA 2021 in NeurIPS 2021
CCF截稿日期
CCF推荐会议每年的举办时间会有稍稍的不同，此列表收集了当年的CCF推荐列表的截稿时间，包括了全部的CCF会议deadline和CCF期刊的special issue, 可作为一个近似参考，详细时间及内容建议查询官网确认。 链接：Call4Papars
Excellent Scholars
- 龙明盛 清华大学
- Judy Hoffman Georgia Tech
- Kate Aaenko Boston University
- 宫博庆 Google Research
- 宫明明 墨尔本大学
- 李晶晶 电子科技大学
- Kuniaki Saito Boston University(Ph.D)
- Zhao Han CMU
- 李汶 ETH
- 张磊 重庆大学
- 庄福振 中科院计算所
- 张宇 南方科技大学
- 王晋东 微软亚洲研究院
- Sinno Jialin Pan NTU
新论文追踪
会议视频
Presentation
- 2021.10 Hoffman, Judy Understanding and Mitigating Bias in Vision Systems 视频
- ECCV 2020 tutorial Domain Adaptation for Visual Applications 视频
- VALSE Webinar 20210609-15 总第241期 领域自适应方法与进展 报告1, 报告2, panel,
- 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
- 吴恩达 NIPS 2016 Nuts and bolts of building AI applications using Deep Learning 视频(需科学上网),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
Novel_papers
1) Novel_papers on transfer learning
| number | Title | Conference/journel + year | Code | Keywords | Benenit for us |
|---|---|---|---|---|---|
| 211 | Learning to Diversify for Single Domain Generalization (paper) | ICCV 2021 | Single DG | ||
| 210 | PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation (paper) | ICCV 2021 | code | UDA | good paper |
| 209 | Semantic Concentration for Domain Adaptation (paper) | ICCV 2021 | UDA | ||
| 208 | Zero-Shot Domain Adaptation with a Physics Prior (paper) | ICCV 2021 | code | zero-shot DA | |
| 207 | BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation (paper) | ICCV 2021 | UDA, Scene Segmentation | ||
| 206 | Domain Generalization via Gradient Surgery (paper) | ICCV 2021 | DG | ||
| 205 | Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate (paper) | ICCV 2021 | UDA | ||
| 204 | Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation (paper) | ICCV 2021 | UDA | ||
| 203 | Improve Unsupervised Pretraining for Few-label Transfer (paper) | ICCV 2021 | pre-train | ||
| 202 | Generalized Source-free Domain Adaptation (paper) | ICCV 2021 | homepage | GSFDA | |
| 201 | Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data (paper) | ICCV 2021 | code | pre-train | |
| 200 | Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling (paper) | ICCV 2021 | |||
| 199 | On Generating Transferable Targeted Perturbations (paper) | ICCV 2021 | code | ||
| 198 | Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder (paper) | ICCV 2021 | cross-domain few shot | ||
| 197 | IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID(paper) | ICCV 2021 | code | UDA, Re-ID | |
| 196 | Universal Cross-Domain Retrieval: Generalizing Across Classes and Domains(paper) | ICCV 2021 | DA, Retrieval | new direction | |
| 195 | Transporting Causal Mechanisms for Unsupervised Domain Adaptation(paper) | ICCV 2021 | code | UDA | good paper |
| 194 | Domain Adaptive Video Segmentation via Temporal Consistency Regularization((paper) | ICCV 2021 | code | video semantic segmentation, UDA | |
| 193 | Dual Path Learning for Domain Adaptation of Semantic Segmentation(paper) | ICCV 2021 | code | UDA, semantic segmentation | |
| 192 | LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation(paper) | ICCV 2021 | active liked UDA, semantic segmentation | new direction | |
| 191 | Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation(paper) | ICCV 2021 | multi target DA, semantic segmentation | ||
| 190 | Multi-Anchor Active Domain Adaptation for Semantic Segmentation(paper) | ICCV 2021 | Active DA, semantic segmentation | ||
| 189 | Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation (paper) | ICCV 2021 | project | SFDA, Semantic Segmentation | |
| 188 | Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency (paper) | ICCV 2021 | DA, 3D detection | ||
| 187 | Vector-Decomposed Disentanglement for Domain-Invariant Object Detection (paper) | ICCV 2021 | DA, object detection | ||
| 186 | Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation (paper) | ACL 2021 | SFDA | good paper, recommended | |
| 185 | cross-domain error minimization for unsupervised domain adaptation (paper) | DASFAA 2021 | code | cross-domain error, UDA | new method from new theory |
| 184 | TIDOT: A Teacher Imitation Learning Approach for Domain Adaptation with Optimal Transport | IJCAI 2021 | UDA | ||
| 183 | Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference | IJCAI 2021 | DG | new problem | |
| 182 | Deep Reinforcement Learning Boosted Partial Domain Adaptation | IJCAI 2021 | Partial DA | ||
| 181 | Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation | IJCAI 2021 | source-free, prototype | ||
| 180 | Adversarial Spectral Kernel Matching for Unsupervised Time Series Domain Adaptation | IJCAI 2021 | ts, da | ||
| 179 | Graph Consistency Based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification (paper) | IJCAI 2021 | UDA, re-id | ||
| 178 | Cross-Domain Few-Shot Classification via Adversarial Task Augmentation (paper) | IJCAI 2021 | code | cross-domain few-shot | |
| 177 | Dual Reweighting Domain Generalization for Face Presentation Attack Detection | IJCAI 2021 | DG, face attack | ||
| 176 | Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metric (paper) | IJCAI 2021 | style transfer | ||
| 176 | DA-GCN: A Domain-aware Attentive Graph Convolution Network for Shared-account Cross-domain Sequential Recommendation (paper) | IJCAI 2021 | cross-domain Recomm | ||
| 175 | Towards Robust Model Reuse in the Presence of Latent Domains | IJCAI 2021 | Model reuse | ||
| 174 | Differentially Private Correlation Alignment for Domain Adaptation | IJCAI 2021 | UDA | ||
| 173 | Residential Electric Load Forecasting via Attentive Transfer of Graph Neural Networks | IJCAI 2021 | GNN | ||
| 172 | Regularising Knowledge Transfer by Meta Functional Learning | IJCAI 2021 | Knowledge transfer | ||
| 171 | KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation (paper) | ICML 2021 | code | MSDA | |
| 170 | A Geometrical Approach to Learning Transferable Representation for Domain Adaptation Regression | ICML 2021 | |||
| 169 | A Bit More Bayesian: Domain-Invariant Learning with Uncertainty (paper) | ICML 2021 | DG | ||
| 168 | Towards Domain-Agnostic Contrastive Learning (paper) | ICML 2021 | DA, contrastive learning | ||
| 167 | f-Domain Adversarial Learning: Theory and Algorithms (paper) | ICML 2021 | UDA | ||
| 166 | Cross-domain Imitation from Observation (paper) | ICML 2021 | DA,RL | ||
| 165 | Unbalanced minibatch Optimal Transport; applications to Domain Adaptation (paper) | ICML 2021 | UDA | ||
| 164 | Domain Generalization using Causal Matching (paper) | ICML 2021 | code | DG | |
| 163 | LAMDA: Label Matching Deep Domain Adaptation (paper) | ICML 2021 | UDA | ||
| 162 | Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts (paper) | ICML 2021 | new problem | ||
| 161 | Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing | ICML 2021 | new problem | ||
| 160 | Zoo-Tuning: Adaptive Transfer from A Zoo of Models | ICML 2021 | fine-tune | ||
| 159 | CARTL: Cooperative Adversarially-Robust Transfer Learning | ICML 2021 | |||
| 158 | Transfer-Based Semantic Anomaly Detection | ICML 2021 | |||
| 157 | Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability | ICML 2021 | |||
| 156 | Function Contrastive Learning of Transferable Meta-Representations (paper) | ICML 2021 | |||
| 155 | Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer Transfer (paper) | ICML 2021 | |||
| 154 | Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation (paper) | CVPR 2021 | |||
| 153 | FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation(paper) | CVPR 2021 | code | augmented domain | new idea |
| 152 | Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation (paper) | CVPR 2021 | code | UDA, instance level | |
| 151 | Transferable Semantic Augmentation for Domain Adaptation (paper) | CVPR 2021 | UDA, data augmentation | ||
| 150 | DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation(paper) | CVPR 2021 | UDA | ||
| 149 | Domain Adaptation with Auxiliary Target Domain-Oriented Classifier(paper) | CVPR 2021 | code | UDA | |
| 148 | MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation(paper) | CVPR 2021 | UDA | ||
| 96 | Progressive Domain Expansion Network for Single Domain Generalization (paper) | CVPR 2021 | code | sigle domain generalization | good idea |
| 147 | Adversarially Adaptive Normalization for Single Domain Generalization (paper) | CVPR 2021 | SDG | ||
| 146 | Uncertainty-Guided Model Generalization to Unseen Domains (paper) | CVPR 2021 | DG, uncertain | new idea | |
| 145 | FSDR: Frequency Space Domain Randomization for Domain Generalization (paper) | CVPR 2021 | DG, frequency domain | new idea | |
| 144 | Few-Shot Image Generation via Cross-Domain Correspondence(paper) | CVPR 2021 | project | few-shot generation | new question |
| 143 | PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training (paper) | CVPR 2021 | |||
| 142 | RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening (paper) | CVPR 2021 | code | DG | |
| 141 | Generalization on Unseen Domains via Inference-Time Label-Preserving Target Projections(paper) | CVPR 2021 | DG | ||
| 140 | Adaptive Methods for Real-World Domain Generalization(paper) | CVPR 2021 | DG | ||
| 139 | A Fourier-Based Framework for Domain Generalization(paper) | CVPR 2021 | DG, fourier | ||
| 138 | Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation (paper) | CVPR 2021 | SSDA | good idea, good paper | |
| 137 | Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation (paper) | CVPR 2021 | SSDA | ||
| 136 | Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation(paper) | CVPR 2021 | |||
| 135 | Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation(paper) | CVPR 2021 | MSDA | ||
| 134 | Dynamic Transfer for Multi-Source Domain Adaptation (paper) | CVPR 2021 | code | MSDA | |
| 133 | Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation (paper) | CVPR 2021 | code | MTDA, graph | |
| 132 | Multi-Target Domain Adaptation With Collaborative Consistency Learning | CVPR 2021 | |||
| 131 | Source-Free Domain Adaptation for Semantic Segmentation (paper) | CVPR 2021 | SFDA+semantic segmentation | ||
| 130 | Unsupervised Multi-Source Domain Adaptation Without Access to Source Data(paper) | CVPR 2021 | MS SFDA | ||
| 129 | Divergence Optimization for Noisy Universal Domain Adaptation(paper) | CVPR 2021 | new porblem | ||
| 128 | Generalized Domain Adaptation () | CVPR 2021 | |||
| 127 | Transferable Query Selection for Active Domain Adaptation (paper) | CVPR 2021 | code | ADA | new scrnario |
| 126 | Dynamic Domain Adaptation for Efficient Inference (paper) | CVPR 2021 | fast inference, UDA | new problem | |
| 125 | Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation(paper) | CVPR 2021 | Open Compound Domain | ||
| 124 | Open Domain Generalization with Domain-Augmented Meta-Learning(paper) | CVPR 2021 | open set; DG | new scrnario | |
| 123 | Prototypical Cross-Domain Self-Supervised Learning for Few-Shot Unsupervised Domain Adaptation(paper) | CVPR 2021 | project | few-shot DA | |
| 122 | Reducing Domain Gap by Reducing Style Bias(paper) | CVPR 2021 | code | style | for mutil tasks |
| 121 | Post-Hoc Uncertainty Calibration for Domain Drift Scenarios(paper) | CVPR 2021 | Calibration, shift | ||
| 120 | Conditional Bures Metric for Domain Adaptation() | CVPR 2021 | |||
| 119 | OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations(paper) | CVPR 2021 | |||
| 118 | Visualizing Adapted Knowledge in Domain Transfer (paper) | CVPR 2021 | code | visualize | good tool |
| 117 | DARCNN: Domain Adaptive Region-Based Convolutional Neural Network for Unsupervised Instance Segmentation in Biomedical Images (paper) | CVPR 2021 | DA + Instance segmentation | ||
| 116 | MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation(paper) | CVPR 2021 | code | UDA, confusion matrix, meta learning | |
| 115 | MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection (paper) | CVPR 2021 | memory,UDA,object detection | ||
| 114 | Group-aware Label Transfer for Domain Adaptive Person Re-identification (paper) | CVPR 2021 | code | UDA,re-id,label group | similar idea with existing paper |
| 113 | Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification (paper) | CVPR 2021 | code | Re-id, DG | |
| 112 | Regressive Domain Adaptation for Unsupervised Keypoint Detection (paper) | CVPR 2021 | code | DA regression | new problem |
| 111 | Domain-robust VQA with diverse datasets and methods but no target labels (paper) | CVPR 2021 | project | VWA, UDA | new scenario |
| 110 | Semantic Segmentation With Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization(paper) | CVPR 2021 | project | SSL, OODG | |
| 109 | Spatio-temporal Contrastive Domain Adaptation for Action Recognition() | CVPR 2021 | |||
| 100 | Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection | CVPR 2021 | |||
| 108 | Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation (paper) | CVPR 2021 | |||
| 107 | Adaptive Cross-Modal Prototypes for Cross-Domain Visual-Language Retrieval() | CVPR 2021 | |||
| 106 | Cross-Domain Similarity Learning for Face Recognition in Unseen Domains(paper) | CVPR 2021 | DG, face | ||
| 105 | Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds(paper) | CVPR 2021 | DG, point cloud | ||
| 104 | Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency (paper) | ICLR 2021 | project | RL, DA, oral | |
| 103 | Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers (paper) | ICLR 2021 | RL, DA, poster | ||
| 102 | Domain-Robust Visual Imitation Learning with Mutual Information Constraints (paper) | ICLR 2021 | RL, DA, poster | ||
| 101 | Domain Generalization with MixStyle (paper) | ICLR 2021 | code | DG, poster | |
| 100 | In Search of Lost Domain Generalization (paper) | ICLR 2021 | code | DG, benchmark, poster | |
| 99 | MetaNorm: Learning to Normalize Few-Shot Batches Across Domains (paper) | ICLR 2021 | code | DG, few-shot, poster | |
| 98 | What Makes Instance Discrimination Good for Transfer Learning? (paper) | ICLR 2021 | project | pre-train, poster | |
| 97 | Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification (paper) | ICLR 2021 | pre-train, poster | ||
| 96 | A Unified Approach to Interpreting and Boosting Adversarial Transferability (paper) | ICLR 2021 | code | Adversarial Transferability, poster | |
| 95 | Self-training For Few-shot Transfer Across Extreme Task Differences (paper) | ICLR 2021 | code | few shot, DA, oral | |
| 94 | Scalable Transfer Learning with Expert Models (paper) | ICLR 2021 | fine-tune, poster | ||
| 93 | Integrating Categorical Semantics into Unsupervised Domain Translation (paper) | ICLR 2021 | code | Domain translation, poster | |
| 92 | Improving Zero-Shot Voice Style Transfer via Disentangled Representation Learning (paper) | ICLR 2021 | Style transfer, poster | ||
| 91 | Tent: Fully Test-Time Adaptation by Entropy Minimization (paper) | ICLR 2021 | code | test-time adaptation | new problem |
| 90 | Self-Supervised Policy Adaptation during Deployment (paper) | ICLR 2021 | RL, adaptation | ||
| 89 | Distance-Based Regularisation of Deep Networks for Fine-Tuning (paper) | ICLR 2021 | fine-tune | ||
| 88 | Contradictory-Structure-Learning-for-Semi-supervised-Domain-Adaptation (paper) | SDM 2021 | code | SS-DA | |
| 87 | Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis | AAAI 2021 | UDA,re-id | similar to our idea | |
| 86 | Exploiting Diverse Characteristics and Adversarial Ambivalence for Domain Adaptive Segmentation (paper) | AAAI 2021 | diverser, UDA | ||
| 85 | Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis (paper) | AAAI 2021 | UDA, application | similar idea with us | |
| 84 | How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches? (paper) | AAAI 2021 | code | UDA, the thidr term of theory | |
| 83 | Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation (paper) | AAAI 2021 | group alignment, UDA | similar idea with us | |
| 82 | Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation (paper) | AAAI 2021 | UDA | improvement for MCD | |
| 81 | A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data (paper) | AAAI 2021 | source-free, Objective detection | ||
| 80 | Unsupervised Domain Adaptation of Black-Box Source Models (paper) | Arvix 2021 | source-free, black | new problem | |
| 79 | Shuffle and Attend: Video Domain Adaptation (paper) | ECCV 2020 | code(not released now) | video DA | |
| 78 | Adversarial Bipartite Graph Learning for Video Domain Adaptation (paper) | MM 2020 | code | video DA | |
| 77 | Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation (paper) | CVPR 2020 | code | video, UDA | |
| 76 | Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay (paper) | arvix 2020 | continual DA | new question | |
| 75 | Continual Learning for Domain Adaptation in Chest X-ray Classification (paper) | MLR 2020(under review) | continual DA | new question | |
| 74 | Continual Domain Adaptation for Machine Reading Comprehension (paper) | CIKM 2020 | continual DA | new question | |
| 73 | Continual Unsupervised Domain Adaptation with Adversarial Learning (paper) | arvix 2020 | continual DA | new question | |
| 72 | Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning (paper) | arvix 2020 | continual DA | new question | |
| 71 | Unsupervised Domain Adaptation without Source Data by Casting a BAIT (paper) | arvix 2020 | source-free DA, prototype | good idea | |
| 70 | A Review of Single-Source Deep Unsupervised Visual Domain Adaptation (paper) | arvix 2020 | DA survey | good further directions | |
| 69 | Supervised Contrastive Learning (paper) | NeurIPS 2020 | code | supervised CL | |
| 68 | Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation (paper) | NeruIPS 2020 | open compound, DA | new problem | |
| 67 | Your Classifier can Secretly Suffice Multi-Source Domain Adaptation (paper) | NeruIPS 2020 | code | MS, prediction agreement | simple yet effective method, new findings |
| 66 | 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 |
| 65 | Unsupervised Domain Adaptation without Source Data by Casting a BAIT(paper) | Arvix 2020 | source-free, two classifiers | good idea | |
| 64 | An Adversarial Domain Adaptation Network for Cross-Domain Fine-Grained Recognition(paper) | WACV 2020 | code | fine-grained, DA | new question |
| 63 | Class-incremental Learning via Deep Model Consolidation (paper) | WACV 2020 | |||
| 62 | 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 | |
| 61 | Measuring Information Transfer in Neural Networks (paper) | arvix 2020 | maybe useful for DA | ||
| 60 | Open-Set Hypothesis Transfer with Semantic Consistency (paper) | arvix 2020 | source free, open set | ||
| 59 | Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks(paper) | arvix 2020 | pretraining | good papers | |
| 58 | Measuring Information Transfer in Neural Networks(paper) | interesting paper | |||
| 57 | 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 | ||
| 56 | 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 | |
| 55 | Graph Optimal Transport for Cross-Domain Alignment (paper) | ICML 2020 | Graph, optimal transport, DA | ||
| 54 | Unsupervised Transfer Learning for Spatiotemporal Predictive Networks (paper) | ICML 2020 | |||
| 53 | Estimating Generalization under Distribution Shifts via Domain-Invariant Representations (paper) | ICML 2020 | code | new theory | recommend to read |
| 52 | Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation (paper) | ICML 2020 | code | ideas from theory | recommend to read |
| 51 | LEEP: A New Measure to Evaluate Transferability of Learned Representations (paper) | ICML 2020 | new metric for transferability | easy to use for other tasks | |
| 50 | Label-Noise Robust Domain Adaptation | ICML2020 | the author is a rising star | ||
| 49 | Progressive Graph Learning for Open-Set Domain Adaptation (paper) | ICML 2020 | code | open set DA | |
| 48 | 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 |
| 47 | Graph Optimal Transport for Cross-Domain Alignment (paper) | ICML 2020 | graph for DA | connenction with GCN | |
| 46 | Learning Deep Kernels for Non-Parametric Two-Sample Tests (paper) | ICML 2020 | code | extend MMD to deep | |
| 45 | Adversarial-Learned Loss for Domain Adaptation | AAAI 2020 | noisy label, adversarial learning | ||
| 44 | Transfer Learning for Anomaly Detection through Localized and Unsupervised Instance Selection | AAAI 2020 | transfer learning, anamaly detection | ||
| 43 | Dynamic Instance Normalization for Arbitrary Style Transfer | AAAI 2020 | dynamic instance normalization | ||
| 42 | AdaFilter: Adaptive Filter Fine-Tuning for Deep Transfer Learning | AAAI 2020 | gated output, fine-tune | ||
| 41 | Bi-Directional Generation for Unsupervised Domain Adaptation | AAAI 2020 | differert feature extractor, different classifiers | connection with ICML, the third term | |
| 40 | Discriminative Adversarial Domain Adaptation | AAAI 2020 | discriminative information with adversarial learning | ||
| 39 | Domain Generalization Using a Mixture of Multiple Latent Domains | AAAI 2020 | |||
| 38 | Multi-Source Distilling Domain Adaptation | AAAI 2020 | multi-source | ||
| 37 | Cross-Modal Cross-Domain Moment Alignment Network for Person Search (paper) | CVPR 2020 | cross-modal, DA, Person search | new problem | |
| 36 | Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision | CVPR 2020 | code | Entropy adversarial based | |
| 35 | Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective | CVPR 2020 | long-tailed | ||
| 34 | Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering | CVPR 2020 | code | cluster | |
| 33 | Stochastic Classifiers for Unsupervised Domain Adaptation | CVPR 2020 | stochastic two classifiers | simialer to MCD | |
| 32 | Progressive Adversarial Networks for Fine-Grained Domain Adaptation | CVPR 2020 | fine-grained | similar to mutil-aspect opinion analysis | |
| 31 | Model Adaptation: Unsupervised Domain Adaptation without Source Data | CVPR 2020 | Recommend to read, new problems | ||
| 30 | Towards Inheritable Models for Open-Set Domain Adaptation | CVPR 2020 | code | ||
| 29 | Unsupervised Domain Adaptation with Hierarchical Gradient Synchronization (paper) | CVPR 2020 | class gropu, DA | new idea | |
| 28 | Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation (paper) | ECCV 2020 | code | SSDA, intar-domain discrepancy | good questions |
| 27 | Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification | ECCV 2020 | |||
| 26 | Extending and Analyzing Self-Supervised Learning Across Domains (paper) | ECCV 2020 | |||
| 25 | Dual Mixup Regularized Learning for Adversarial Domain Adaptation (paper) | ECCV 2020 | |||
| 24 | 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 |
| 23 | Class-Incremental Domain Adaptation(paper) | ECCV 2020 | new problems | ||
| 22 | Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation (paper) | ACM MM 2020 | code | ||
| 21 | Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition (paper) | ACM MM 2020 | similar idea with us | ||
| 20 | Do Adversarially Robust ImageNet Models Transfer Better? | arvix 2020 | code | Many experiments | |
| 19 | Visualizing Transfer Learning | arvix 2020 | interesting | ||
| 18 | A SURVEY ON DOMAIN ADAPTATION THEORY:LEARNING BOUNDS AND THEORETICAL GUARANTEES (paper) | arvix 2020 | theory | ||
| 17 | Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification (paper) | arvix 2020 | Good ideas | ||
| 16 | Towards Recognizing Unseen Categories in Unseen Domains (paper) | arvix 2020 | new problems | ||
| 15 | MiCo: Mixup Co-Training for Semi-Supervised Domain Adaptation (paper) | arvix 2020 | good framework | ||
| 14 | Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning (paper | arvix 2020 | |||
| 13 | Learning from a Complementary-label Source Domain: Theory and Algorithms(paper) | arvix 2020 | code | novel idea | |
| 12 | 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 | |
| 11 | Neural transfer learning for natural language processing（paper) | 2019 PDH thesis | NLP, transfer lerning | very detailed related work | |
| 10 | Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation (paper) | ICCV 2019 | code | Cluster assumption, DA | deal with misclassified samples |
| 9 | SpotTune: Transfer Learning through Adaptive Fine-tuning (paper) | CVPR 2019 | code | dynamic routing is a general method | |
| 8 | Parameter Transfer Unit for Deep Neural Networks (paper) | PAKDD 2019 best paper | good idea, recommened to read | ||
| 7 | Heterogeneous Domain Adaptation via Soft Transfer Network (paper) | ACM MM 2019 | |||
| 6 | DARec: Deep Domain Adaptation for Cross-Domain Recommendation via Transferring Rating Patterns (paper) | IJCAI 2019 | DA, cross-domain recommendation | classical work | |
| 5 | Adversarial Domain Adaptation with Domain Mixup (paper) | IJCAI 2019 | mix-ip, DA | new idea | |
| 4 | Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (paper) | ICCV 2019 | code | video, DA | the first work with large dataset |
| 3 | PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation (paper) | NeurIPS 2019 | code | DA, point cloud | |
| 2 | Incremental Adversarial Domain Adaptation for Continually Changing Environments (paper) | ICRA 2018 | continual DA | new question | |
| 1 | ADAPTING TO CONTINUOUSLY SHIFTING DOMAINS (paper) | ICLR 2018 workshop | continual DA | new question | |
| 0 | Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation (paper) | ICML 2012 |
2) Novel_papers on related fileds
| number | Title | Conference/journel + year | Code | Keywords | Benenit for us |
|---|---|---|---|---|---|
| 22 | MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks (paper) | ICCV 2021 | data augmentation | ||
| 21 | Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain (paper) | ICCV 2021 | code | data augmentation | maybe useful for UDA |
| 20 | OpenWGL: Open-World Graph Learning (paper) | ICDM 2020 | open node classification | best student paper | |
| 19 | FREE LUNCH FOR FEW-SHOT LEARNING: DISTRIBUTION CALIBRATION (paper) | ICLR 2021 | code | calibation | maybe for UDA |
| 18 | Semi-Supervised Action Recognition with Temporal Contrastive Learning(paper) | CVPR 2021 | project | action recognition | |
| 17 | Continual Adaptation of Visual Representations via Domain Randomization and Meta-Learning (paper) | CVPR 2021 | |||
| 16 | Wasserstein-2 Generative Networks (paper) | ICLR 2021 | GAN， wassertein | ||
| 15 | Prototypical Contrastive Learning of Unsupervised Representations(paper) | ICLR 2021 | prototype, constractive learning | maybe for UDA | |
| 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 |
Workshop collection
| Title | Conference + year | speaker | Benenit for us |
|---|---|---|---|
| Learning from Imperfect Data (link) | CVPR 2020 | ||
| Cross-Domain Few-Shot Learning (CD-FSL) Challenge (link) | CVPR 2020 | ||
| Uncertainty and Robustness in Deep Learning Workshop (link) | ICML 2020 |