# Domain Adaptation, Generalization, Out-of-Distribution and Debiasing

## Domain Adaptation
- [2014 ICML] **Heterogeneous Domain Adaptation for Multiple Classes**, [[paper]](http://proceedings.mlr.press/v33/zhou14.pdf), [[bibtex]](/Bibtex/Heterogeneous%20Domain%20Adaptation%20for%20Multiple%20Classes.bib).
- [2015 ICML] **Unsupervised Domain Adaptation by Backpropagation**, [[paper]](http://proceedings.mlr.press/v37/ganin15.pdf), [[bibtex]](/Bibtex/Unsupervised%20Domain%20Adaptation%20by%20Backpropagation.bib), sources: [[shucunt/domain_adaptation]](https://github.com/shucunt/domain_adaptation), [[pumpikano/tf-dann]](https://github.com/pumpikano/tf-dann), [[kskdev/DANN]](https://github.com/kskdev/DANN), [[fungtion/DANN]](https://github.com/fungtion/DANN).
- [2016 NIPS] **Domain Separation Networks**, [[paper]](https://papers.nips.cc/paper/6254-domain-separation-networks.pdf), [[bibtex]](/Bibtex/Domain%20Separation%20Networks.bib), sources: [[tensorflow/models/research/domain_adaptation]](https://github.com/tensorflow/models/tree/master/research/domain_adaptation), [[fungtion/DSN]](https://github.com/fungtion/DSN), [[wj926/DomainSeparationNetworks]](https://github.com/wj926/DomainSeparationNetworks).
- [2016 JMLR] **Domain-Adversarial Training of Neural Networks**, [[paper]](http://jmlr.org/papers/volume17/15-239/15-239.pdf), [[bibtex]](/Bibtex/Domain-Adversarial%20Training%20of%20Neural%20Networks.bib), sources: [[shucunt/domain_adaptation]](https://github.com/shucunt/domain_adaptation), [[pumpikano/tf-dann]](https://github.com/pumpikano/tf-dann), [[kskdev/DANN]](https://github.com/kskdev/DANN), [[fungtion/DANN]](https://github.com/fungtion/DANN).
- [2018 NIPS] **Conditional Adversarial Domain Adaptation**, [[paper]](https://papers.nips.cc/paper/7436-conditional-adversarial-domain-adaptation.pdf), [[bibtex]](/Bibtex/Conditional%20Adversarial%20Domain%20Adaptation.bib), sources: [[thuml/CDAN]](https://github.com/thuml/CDAN).
- [2019 JMLR] **Multi-class Heterogeneous Domain Adaptation**, [[paper]](http://jmlr.org/papers/volume20/13-580/13-580.pdf), [[bibtex]](/Bibtex/Multi-class%20Heterogeneous%20Domain%20Adaptation.bib).
- [2019 ICML] **On Learning Invariant Representations for Domain Adaptation**, [[paper]](http://proceedings.mlr.press/v97/zhao19a/zhao19a.pdf), [[bibtex]](/Bibtex/On%20Learning%20Invariant%20Representations%20for%20Domain%20Adaptation.bib).
- [2020 AAAI] **Unsupervised Domain Adaptation on Reading Comprehension**, [[paper]](https://arxiv.org/pdf/1911.06137.pdf), [[bibtex]](/Bibtex/Unsupervised%20Domain%20Adaptation%20on%20Reading%20Comprehension.bib), sources: [[caoyu1991/CASe]](https://github.com/caoyu1991/CASe).
- [2020 ArXiv] **Tackling Unsupervised Multi-source Domain Adaptation with Optimism and Consistency**, [[paper]](https://arxiv.org/pdf/2009.13939.pdf), [[bibtex]](/Bibtex/Tackling%20unsupervised%20multi-source%20domain%20adaptation%20with%20optimism%20and%20consistency.bib), sources: [[dpernes/modafm]](https://github.com/dpernes/modafm).
- [2021 ICML] **Delving into Deep Imbalanced Regression**, [[paper]](https://arxiv.org/pdf/2102.09554.pdf), [[bibtex]](/Bibtex/Delving%20into%20Deep%20Imbalanced%20Regression.bib), sources: [[YyzHarry/imbalanced-regression]](https://github.com/YyzHarry/imbalanced-regression).
- [2021 ICCV] **Transporting Causal Mechanisms for Unsupervised Domain Adaptation**, [[paper]](https://arxiv.org/pdf/2107.11055.pdf), [[bibtex]](/Bibtex/Transporting%20Causal%20Mechanisms%20for%20Unsupervised%20Domain%20Adaptation.bib), sources: [[yue-zhongqi/tcm]](https://github.com/yue-zhongqi/tcm).
- [2021 NAACL] **Domain Divergences: A Survey and Empirical Analysis**, [[paper]](https://aclanthology.org/2021.naacl-main.147.pdf), [[bibtex]](/Bibtex/Domain%20Divergences%20-%20A%20Survey%20and%20Empirical%20Analysis.bib).

## Domain Generalization
- [2016 AAAI] **Return of Frustratingly Easy Domain Adaptation**, [[paper]](https://arxiv.org/pdf/1511.05547.pdf), [[bibtex]](/Bibtex/Return%20of%20Frustratingly%20Easy%20Domain%20Adaptation.bib).
- [2018 AAAI] **Learning to Generalize: Meta-Learning for Domain Generalization**, [[paper]](https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16067/16547), [[bibtex]](/Bibtex/Learning%20to%20Generalize%20-%20Meta-Learning%20for%20Domain%20Generalization.bib), sources: [[HAHA-DL/MLDG]](https://github.com/HAHA-DL/MLDG).
- [2019 ICML] **Domain Agnostic Learning with Disentangled Representations**, [[paper]](http://proceedings.mlr.press/v97/peng19b/peng19b.pdf), [[bibtex]](/Bibtex/Domain%20Agnostic%20Learning%20with%20Disentangled%20Representations.bib), [[supplementary]](http://proceedings.mlr.press/v97/peng19b/peng19b-supp.pdf), sources: [[VisionLearningGroup/DAL]](https://github.com/VisionLearningGroup/DAL).
- [2019 ICCV] **Episodic Training for Domain Generalization**, [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_Episodic_Training_for_Domain_Generalization_ICCV_2019_paper.pdf), [[bibtex]](/Bibtex/Episodic%20Training%20for%20Domain%20Generalization.bib), sources: [[HAHA-DL/Episodic-DG]](https://github.com/HAHA-DL/Episodic-DG).
- [2019 NeurIPS] **Domain Generalization via Model-Agnostic Learning of Semantic Features**, [[paper]](https://papers.nips.cc/paper/8873-domain-generalization-via-model-agnostic-learning-of-semantic-features.pdf), [[bibtex]](/Bibtex/Domain%20Generalization%20via%20Model-Agnostic%20Learning%20of%20Semantic%20Features.bib), sources: [[biomedia-mira/masf]](https://github.com/biomedia-mira/masf).

## Out-of-Distribution Learning
- [2020 NeurIPS] **Energy-based Out-of-distribution Detection**, [[paper]](https://proceedings.neurips.cc/paper/2020/file/f5496252609c43eb8a3d147ab9b9c006-Paper.pdf), [[bibtex]](/Bibtex/Energy-based%20Out-of-distribution%20Detection.bib), sources: [[wetliu/energy_ood]](https://github.com/wetliu/energy_ood).
- [2020 ArXiv] **Out-of-Distribution Generalization via Risk Extrapolation**, [[paper]](https://arxiv.org/pdf/2003.00688.pdf), [[bibtex]](/Bibtex/Out-of-Distribution%20Generalization%20via%20Risk%20Extrapolation.bib), sources: [[capybaralet/REx_code_release]](https://github.com/capybaralet/REx_code_release).
- [2020 ArXiv] **Unshuffling Data for Improved Generalization**, [[paper]](https://arxiv.org/pdf/2002.11894.pdf), [[bibtex]](/Bibtex/Unshuffling%20Data%20for%20Improved%20Generalization.bib).
- [2020 ICLR] **Your classifier is secretly an energy based model and you should treat it like one**, [[paper]](https://openreview.net/pdf?id=Hkxzx0NtDB), [[bibtex]](/Bibtex/Your%20classifier%20is%20secretly%20an%20energy%20based%20model%20and%20you%20should%20treat%20it%20like%20one.bib), sources: [[wgrathwohl/JEM]](https://github.com/wgrathwohl/JEM).
- [2021 ICML] **Improved OOD Generalization via Adversarial Training and Pre-training**, [[paper]](http://proceedings.mlr.press/v139/yi21a/yi21a.pdf), [[bibtex]](/Bibtex/Improved%20OOD%20Generalization%20via%20Adversarial%20Training%20and%20Pre-training.bib), [[supplementary]](http://proceedings.mlr.press/v139/yi21a/yi21a-supp.pdf).
- [2021 ArXiv] **The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning**, [[paper]](https://arxiv.org/pdf/2106.15831.pdf), [[bibtex]](/Bibtex/The%20Evolution%20of%20Out-of-Distribution%20Robustness%20Throughout%20Fine-Tuning.bib).

## Debiasing
- [2020 ICML] **Learning De-biased Representations with Biased Representations**, [[paper]](http://proceedings.mlr.press/v119/bahng20a/bahng20a.pdf), [[bibtex]](/Bibtex/Learning%20De-biased%20Representations%20with%20Biased%20Representations.bib), sources: [[clovaai/rebias]](https://github.com/clovaai/rebias).
- [2020 NeurIPS] **Learning from Failure: Training Debiased Classifier from Biased Classifier**, [[paper]](https://proceedings.neurips.cc/paper/2020/file/eddc3427c5d77843c2253f1e799fe933-Paper.pdf), [[bibtex]](/Bibtex/Learning%20from%20Failure%20-%20Training%20Debiased%20Classifier%20from%20Biased%20Classifier.bib), sources: [[alinlab/LfF]](https://github.com/alinlab/LfF).