Domain Alignment-Based Methods

• [ECMLPKDD 2019
• [arXiv 2020
• [arXiv 2020
• [PR 2020 - DA-DG)] (**CAADA**) [80]
• [AAAI 2020 - tokyo/dg_mmld)] [83]
• [ISBI 2020
• [ICPR 2020
• [UAI 2020 - Discriminant-Analysis)] (**MDA**) [70]
• [NeurIPS 2020
• [NeurIPS 2020 - zhao/DG_via_ER)] [86]
• [arXiv 2021
• [IJCAI 2021
• [ICCV 2021
• [TMLR 2022
• [ICML 2013 - dica)] (**DICA**) [65]
• [JMLR 2016
• [CVPR 2016
• [IJCAI 2016
• [TPAMI 2017
• [ICCV 2017
• [arXiv 2018
• [AAAI 2018
• [CVPR 2018 - AAE**) [76]
• [ECCV 2018
• [arXiv 2019
• [arXiv 2019
• [MICCAI 2019
• [arXiv 2019
• [arXiv 2020
• [arXiv 2021
• [IJCAI 2021
• [TMLR 2022

Inference-Time-Based Methods

• [CVPR 2021 - Polaris/InferenceTimeDG)] [118]
• [CVPR 2021 - ERM**) [132]
• [NeurIPS 2021

Data Augmentation-Based Methods

• [arXiv 2017 - lab/certifiable-distributional-robustness)] [52]
• [ICLR 2018
• [NeurIPS 2018 - unseen-domains)] [25]
• [WACV 2019 - DG)] [167]
• [ICCV 2019 - shift-robustness)] [21]
• [ICCV 2019
• [ICCV workshop 2019
• [arXiv 2020
• [Frontiers in Cardiovascular Medicine 2020
• [TMI 2020
• [ICPR 2020
• [arXiv 2021 - release)] (**MixStyle**) [58]
• [TPAMI 2021
• [ICLR 2021
• [CVPR 2021
• [ICCV 2021
• [ICLR 2022
• [Frontiers in Bioengineering and Biotechnology 2019
• [arXiv 2020
• [ICLR 2022
• [TPAMI 2021
• [ICCV 2019

Disentangled Representation Learning-Based Methods

• [arXiv 2021
• [AAAI 2021
• [ICIP 2021
• [ECCV 2012 - bias)] [103]
• [ICML workshop 2019 - Amsterdam/DIVA)] (**DIVA**) [107]
• [ICML 2020
• [ECCV 2020
• [CVPR 2021
• [CVPR 2021
• [ICCV 2021
• [ICCV 2021
• [MM 2021
• [TMLR 2022
• [TMLR 2022
• [ICIP 2021
• [AAAI 2021
• [arXiv 2021

Self-Supervised Learning-Based Methods

• [MM 2021
• [arXiv 2020
• [BMVC 2020
• [TPAMI 2021 - Supervised_Learning_Across_Domains)] [101]
• [ICONIP 2021
• [ICCV 2021
• [MICCAI 2021
• [ICONIP 2021
• [AAAI Student Abstract 2021
• [MICCAI 2021
• [NeurIPS 2021
• [CVPR 2019
• [ICLR 2020
• [ECCV 2020 - sjwang/EISNet)] (**EISNet**) [99]

Meta-Learning-Based Methods

• [AAAI 2018 - DL/MLDG)] (**MLDG**) [1]
• [arXiv 2020 - RIPL/DomainGeneralization-Stylization)] [60]
• [TNNLS 2020
• [MICCAI 2020
• [ICIP 2021 - EML**) [180]
• [arXiv 2021
• [ICIP 2021 - EML**) [180]
• [NeurIPS 2019 - mira/masf)] (**MASF**) [18]
• [MICCAI 2020
• [arXiv 2021

Information-Based Methods

• [ECCV 2020
• [ECCV 2020
• [NeurIPS 2021

Ensemble Learning-Based Methods

• [ECCV 2014
• [TNNLS 2018
• [TIP 2017
• [IEEE Robotics and Automation Letters 2018
• [GCPR 2018 - SAMs**) [92]
• [ICIP 2018
• [TMI 2020
• [TMI 2020 - Net)] (**MS-Net**) [95]
• [ICLR workshop 2021
• [arXiv 2021
• [arXiv 2021
• [MM 2021
• [ICLR workshop 2021
• [arXiv 2021

• [109 - 009-5152-4.pdf))] [[112]](https://proceedings.neurips.cc/paper/2020/file/d8330f857a17c53d217014ee776bfd50-Paper.pdf), domain generalization [[113](https://proceedings.neurips.cc/paper/2011/file/b571ecea16a9824023ee1af16897a582-Paper.pdf)] aims to learn a model from source domain(s) and make it generalize well to unknown target domains.

Regularization-Based Methods

• [ICCV 2021
• [NeurIPS 2011
• [ICLR 2020
• [ECCV 2020
• [NeurIPS 2020 - OOD)] [181]
• [arXiv 2021
• [arXiv 2021
• [arXiv 2021
• [ICLR 2021
• [ICCV 2021
• [NeurIPS 2021
• [NeurIPS 2021 - for-the-Future)] (**GI**) [204]
• [NeurIPS 2021
• [NeurIPS 2021
• [ICLR 2022
• [ICML 2022
• [ICLR 2021
• [ICLR 2020
• [arXiv 2021
• [arXiv 2021
• [ICLR 2022
• [ICML 2022
• [NeurIPS 2021
• [CVPR 2021 - SJTU/FACT)] (**FACT**) [160]
• [NeurIPS 2018

Normalization-Based Methods

• [ECCV 2016
• [WACV 2022 - Net**) [186]
• [ECCV 2016
• [ECCV 2020
• [ICLR 2021 - AI/MetaNorm)] (**MetaNorm**) [19]
• [arXiv 2020

Causality-Based Methods

• [AAAI 2022
• [arXiv 2021 - DG**) [163]
• [TPAMI 2021
• [CVPR 2021
• [ICCV 2021
• [NeurIPS 2021 - semantic-generative-model)] (**CSG-ind**) [145]
• [NeurIPS 2021
• [arXiv 2022 - CORAL**, **CausIRL-MMD**) [216]
• [arXiv 2021 - DG**) [163]
• [TPAMI 2021
• [arXiv 2022 - CORAL**, **CausIRL-MMD**) [216]
• [NeurIPS 2021
• [ICML 2021
• [NeurIPS 2021 - IRM)] (**IB-ERM**, **IB-IRM**) [207]
• [arXiv 2022
• [AAAI 2022
• [arXiv 2019
• [ICML 2021

Neural Architecture Search-based Methods

• [ICCV 2021 - OoD**) [129]

Neural Architecture Search-based Methods

• [CVPR 2021
• [CVPR 2021
• [CVPR 2021
• [WACV 2023
• [CVPR 2020 - ADA)] (**M-ADA**) [27]
• [arXiv 2021
• [WACV 2023
• [ICCV 2021

Face Recognition & Anti-Spoofing

• [CVPR 2020
• [CVPR 2020
• [CVPR 2020 - pei/SSDG-CVPR2020)] (**SSDG**) [79]
• [CVPR 2019 - MADDoG)] (**MADDG**) [78]

Person Re-Identification

• [TPAMI 2021 - person-reid)] [114]
• [TIP 2021 - AAE**) [144]
• [CVPR 2021
• [TPAMI 2021 - person-reid)] [114]
• [AAAI 2020
• [CVPR 2021
• [CVPR 2021
• [NeurIPS 2021
• [ICLR 2021 - release)] (**MixStyle**) [56]

Neural Architecture Search-based Methods

• [ICASSP 2020
• [CVPR 2021 - DAML)] (**DAML**) [119]
• [ICASSP 2020
• [ICCV 2019 - DL/Episodic-DG)] (**Epi-FCR**) [7]
• [ICML 2019 - Critic**) [5]
• [ECCV 2020
• [ICCV 2021

Life-Long Learning

• [ECCV workshop 2020 - MLDG**) [14]
• [CVPR 2021 - DR**) [153]
• [165
• [28 - cn-beijing.aliyuncs.com/CNN%E5%AD%A6%E4%B9%A0%E7%B3%BB%E5%88%97/Gradient-Based_Learning_Applied_to_Document_Recognition.pdf), MNIST-M [[30](http://proceedings.mlr.press/v37/ganin15.pdf)], SVHN [[31](https://research.google/pubs/pub37648.pdf)], SYN [[30](http://proceedings.mlr.press/v37/ganin15.pdf)]}; 24,000 samples; 10 classes | [21], [25], [27], [28], [34], [35], [55], [59], [63], [94], [98], [116], [118], [130], [141], [142], [146], [151], [153], [157], [158], [159], [160], [166], [168], [179], [189], [203], [209], [210] |
• [32 - cFUrfEo/view)) | Object recognition; 4 domains: {Amazon, Webcam, DSLR, Caltech}; 4,652 samples in 31 classes (office31) or 2,533 samples in 10 classes (office31+caltech); 51 MB | [6], [35], [67], [68], [70], [71], [80], [91], [96], [119], [131], [167] |
• [20 - 2SNWq0CDAuWOBRRBL7ZZsw)) | Object recognition; 4 domains: {Art, Clipart, Product, Real World}; 15,588 samples of dimension (3, 224, 224); 65 classes; 1.1 GB | [19], [54], [28], [34], [55], [58], [60], [61], [64], [80], [92], [94], [98], [101], [118], [126], [130], [131], [132], [133], [137], [138], [140], [146], [148], [156], [159], [160], [162], [163], [167], [173], [174], [178], [179], [182], [184], [189], [190], [199], [201], [202], [203], [206], [211], [212], [214], [216], [217], [220], [222], [223], [224], [230] |
• [36 - to-real generalization; 280,157 samples | [119], [182] |
• [37
• [44
• [45 - camera-traps)) | Animal classification; 4 domains captured at different geographical locations: {L100, L38, L43, L46}; 24,788 samples of dimension (3, 224, 224); 10 classes; 6.0 GB + 8.6 MB | [132], [136], [138], [140], [173], [201], [202], [207], [212], [214], [216], [222], [223], [224] |
• [40 - HMDB.pdf?sequence=1&isAllowed=y)] | Action recognition | 2 domains with 12 overlapping actions; 3809 samples | | -->
• [48 - spoofing | Combination of 4 face anti-spoofing datasets | | -->
• DeepDG (jindongwang)
• 155 - ppt.pdf)] *(Jindong Wang (MSRA), in Chinese)*
• jindongwang
• [PhD 2020, Kaiyang Zhou (University of Surrey)
• [39
• [6
• [16 - FeiCompVIsImageU2007.pdf), LabelMe [[9]](https://idp.springer.com/authorize/casa?redirect_uri=https://link.springer.com/content/pdf/10.1007/s11263-007-0090-8.pdf&casa_token=n3w4Sen-huAAAAAA:sJY2dHreDGe2V4KE9jDehftM1W-Sn1z8bqeF_WK8Q9t4B0dFk5OXEAlIP7VYnr8UfiWLAOPG7dK0ZveYWs8), PASCAL [[10]](https://idp.springer.com/authorize/casa?redirect_uri=https://link.springer.com/content/pdf/10.1007/s11263-009-0275-4.pdf&casa_token=Zb6LfMuhy_sAAAAA:Sqk_aoTWdXx37FQjUFaZN9ZMQxrUhqO2S_HbOO2a9BKtejW7CMekg-3PDVw6Yjw7BZqihyjP0D_Y6H2msBo), SUN [[11]](https://dspace.mit.edu/bitstream/handle/1721.1/60690/Oliva_SUN%20database.pdf?sequence=1&isAllowed=y)}; 10,729 samples of dimension (3, 224, 224); 5 classes; about 3.6 GB | [2], [6], [7], [14], [15], [18], [60], [61], [64], [67], [68], [70], [71], [74], [76], [77], [81], [83], [86], [91], [98], [99], [101], [102], [103], [117], [118], [126], [127], [131], [132], [136], [138], [140], [142], [145], [146], [148], [149], [161], [170], [173], [174], [184], [190], [195], [199], [201], [202], [203], [209], [216], [217], [222], [223], [224] |
• [33 - source/groundtruth/clipart.zip), [infograph](http://csr.bu.edu/ftp/visda/2019/multi-source/infograph.zip), [painting](http://csr.bu.edu/ftp/visda/2019/multi-source/groundtruth/painting.zip), [quick-draw](http://csr.bu.edu/ftp/visda/2019/multi-source/quickdraw.zip), [real](http://csr.bu.edu/ftp/visda/2019/multi-source/real.zip), and [sketch](http://csr.bu.edu/ftp/visda/2019/multi-source/sketch.zip); or [original](http://ai.bu.edu/M3SDA/)) | Object recognition; 6 domains: {clipart, infograph, painting, quick-draw, real, sketch}; 586,575 samples of dimension (3, 224, 224); 345 classes; 1.2 GB + 4.0 GB + 3.4 GB + 439 MB + 5.6 GB + 2.5 GB | [34], [57], [69], [104], [119], [130], [131], [132], [133], [138], [140], [150], [173], [182], [189], [201], [202], [203], [216], [222], [223], [224], [230] |
• [35
• [34
• [38
• [43 - to-real generalization; 29,966 samples | [62], [115], [185], [193] |
• [46 - 3-319-48881-3_2) | Person re-idetification; cross-dataset re-ID; heterogeneous DG with 2 domains; 69,079 samples | [12], [13], [28], [55], [56], [58], [114], [144], [187], [208] |
• [ECCV workshop 2020 - MLDG**) [14]
• [28 - cn-beijing.aliyuncs.com/CNN%E5%AD%A6%E4%B9%A0%E7%B3%BB%E5%88%97/Gradient-Based_Learning_Applied_to_Document_Recognition.pdf), MNIST-M [[30](http://proceedings.mlr.press/v37/ganin15.pdf)], SVHN [[31](https://research.google/pubs/pub37648.pdf)], SYN [[30](http://proceedings.mlr.press/v37/ganin15.pdf)]}; 24,000 samples; 10 classes | [21], [25], [27], [28], [34], [35], [55], [59], [63], [94], [98], [116], [118], [130], [141], [142], [146], [151], [153], [157], [158], [159], [160], [166], [168], [179], [189], [203], [209], [210] |
• [42
• [2 - 2fvpQY_QSyJf2uIECzqPuQ)) | Object recognition; 4 domains: {photo, art_painting, cartoon, sketch}; 9,991 samples of dimension (3, 224, 224); 7 classes; 174 MB | [1], [2], [4], [5], [14], [15], [18], [19], [34], [54], [28], [35], [55], [56], [57], [58], [59], [60], [61], [64], [69], [73], [77], [80], [81], [82], [83], [84], [86], [90], [92], [94], [96], [98], [99], [101], [102], [104], [105], [116], [117], [118], [127], [129], [130], [131], [132], [136], [137], [138], [139], [140], [142], [145], [146], [148], [149], [153], [156], [157], [158], [159], [160], [161], [162], [163], [167], [170], [171], [173], [174], [178], [179], [180], [182], [184], [189], [190], [195], [199], [200], [201], [202], [203], [206], [209], [210], [211], [212], [214], [216], [217], [220], [222], [223], [224], [230] |

Neural Architecture Search-based Methods

• [IEEE Transactions on Instrumentation and Measurement 2020
• [arXiv 2021
• [IJCV 2022
• [arXiv 2020
• [TNNLS 2017
• [arXiv 2020
• [MM 2022
• [NeurIPS workshop 2021
• [CVPR 2015
• [arXiv 2021 - benchmark)] (**StyleMatch**) [54]
• [arXiv 2021
• [IJCV 2022
• [CVPR 2022
• [arXiv 2021
• [CVPR 2022

Neural Architecture Search-based Methods

• [CVPR 2021 - ELCFS)] (**FedDG**) [147]
• [arXiv 2021
• [ICCV 2021
• [arXiv 2021