diff --git a/README.md b/README.md index 6f722e2..72dcf20 100644 --- a/README.md +++ b/README.md @@ -29,6 +29,7 @@ If you would like to contribute to our repository or have any questions/advice, - [Semi/Weak/Un-Supervised Domain Generalization](#semiweakun-supervised-domain-generalization) - [Open/Heterogeneous Domain Generalization](#openheterogeneous-domain-generalization) - [Federated Domain Generalization](#federated-domain-generalization) + - [Source-free Domain Generalization](#source-free-domain-generalization) - [Applications](#applications) - [Person Re-Identification](#person-re-identification) - [Face Recognition \& Anti-Spoofing](#face-recognition--anti-spoofing) @@ -412,6 +413,11 @@ If you would like to contribute to our repository or have any questions/advice, - FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space [[CVPR 2021](http://openaccess.thecvf.com/content/CVPR2021/papers/Liu_FedDG_Federated_Domain_Generalization_on_Medical_Image_Segmentation_via_Episodic_CVPR_2021_paper.pdf)] [[Code](https://github.com/liuquande/FedDG-ELCFS)] (**FedDG**) [147] - Collaborative Optimization and Aggregation for Decentralized Domain Generalization and Adaptation [[ICCV 2021](https://openaccess.thecvf.com/content/ICCV2021/papers/Wu_Collaborative_Optimization_and_Aggregation_for_Decentralized_Domain_Generalization_and_Adaptation_ICCV_2021_paper.pdf)] (**COPDA**) [159] +## Source-free Domain Generalization +> Source-free domain generalization aims to improve model's generalization capability to arbitrary unseen domains without exploiting any source domain data. + +- PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization [[ICCV 2023](https://arxiv.org/abs/2307.15199)] [[Project Page](https://PromptStyler.github.io/)] (**PromptStyler**) [231] + ## Applications ### Person Re-Identification - Deep Domain-Adversarial Image Generation for Domain Generalisation [[AAAI 2020](https://ojs.aaai.org/index.php/AAAI/article/download/7003/6857)] [[Code](https://github.com/KaiyangZhou/Dassl.pytorch)] @@ -448,7 +454,7 @@ If you would like to contribute to our repository or have any questions/advice, | 2020 | **ICLR:** [55], [83], [218]; **ICLR:** [126]; **CVPR:** [22], [27], [79], [106]; **ICML:** [105]; **ECCV:** [14], [15], [28], [57], [64], [94], [99], [104]; **NeurIPS:** [75], [86], [112], [181] | | 2021 | **ICLR:** [19], [56], [59], [134], [175], [196]; **ICLR:** [139], [171], [221]; **CVPR:** [12], [13], [115], [116], [117], [118], [119], [132], [141], [147], [153], [160], [168], [187], [193]; IJCAI: [155], [195], [230]; **ICML:** [73], [190], [217]; **ICCV:** [129], [130], [133], [135], [138], [142], [143], [148], [149], [150], [158], [159], [194]; **MM:** [131], [137], [146], [157]; **NeurIPS:** [136], [145], [152], [154], [198], [199], [200], [201], [202], [203], [204], [205], [206], [207], [208], [228], [225] | | 2022 | **AAAI:** [140]; **ICLR:** [213], [224]; **CVPR:** [69], [182], [214]; **ICML**: [173]; **MM:** [211] | -| 2023 | **WACV:** [215]; **ICLR:** [223] | +| 2023 | **WACV:** [215]; **ICLR:** [223]; **ICCV:** [231] | | Top Journal | Papers | | ---- | ---- | @@ -483,11 +489,11 @@ If you would like to contribute to our repository or have any questions/advice, | **Colored MNIST** [[165]](https://arxiv.53yu.com/pdf/1907.02893.pdf) | Handwritten digit recognition; 3 domains: {0.1, 0.3, 0.9}; 70,000 samples of dimension (2, 28, 28); 2 classes | [82], [138], [140], [149], [152], [154], [165], [171], [173], [190], [200], [202], [214], [216], [217], [219], [220], [222], [224] | | **Rotated MNIST** [[6]](http://openaccess.thecvf.com/content_iccv_2015/papers/Ghifary_Domain_Generalization_for_ICCV_2015_paper.pdf) ([original](https://github.com/Emma0118/mate)) | Handwritten digit recognition; 6 domains with rotated degree: {0, 15, 30, 45, 60, 75}; 7,000 samples of dimension (1, 28, 28); 10 classes | [5], [6], [15], [35], [53], [55], [63], [71], [73], [74], [76], [77], [86], [90], [105], [107], [138], [140], [170], [173], [202], [204], [206], [216], [222], [224] | | **Digits-DG** [[28]](https://arxiv.org/pdf/2007.03304) | Handwritten digit recognition; 4 domains: {MNIST [[29]](http://lushuangning.oss-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] | -| **VLCS** [[16]](http://openaccess.thecvf.com/content_iccv_2013/papers/Fang_Unbiased_Metric_Learning_2013_ICCV_paper.pdf) ([1](https://drive.google.com/uc?id=1skwblH1_okBwxWxmRsp9_qi15hyPpxg8); or [original](https://www.mediafire.com/file/7yv132lgn1v267r/vlcs.tar.gz/file)) | Object recognition; 4 domains: {Caltech [[8]](http://www.vision.caltech.edu/publications/Fei-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] | +| **VLCS** [[16]](http://openaccess.thecvf.com/content_iccv_2013/papers/Fang_Unbiased_Metric_Learning_2013_ICCV_paper.pdf) ([1](https://drive.google.com/uc?id=1skwblH1_okBwxWxmRsp9_qi15hyPpxg8); or [original](https://www.mediafire.com/file/7yv132lgn1v267r/vlcs.tar.gz/file)) | Object recognition; 4 domains: {Caltech [[8]](http://www.vision.caltech.edu/publications/Fei-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], [231] | | **Office31+Caltech** [[32]](https://linkspringer.53yu.com/content/pdf/10.1007/978-3-642-15561-1_16.pdf) ([1](https://drive.google.com/file/d/14OIlzWFmi5455AjeBZLak2Ku-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] | -| **OfficeHome** [[20]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Venkateswara_Deep_Hashing_Network_CVPR_2017_paper.pdf) ([1](https://drive.google.com/uc?id=1uY0pj7oFsjMxRwaD3Sxy0jgel0fsYXLC); or [original](https://drive.google.com/file/d/0B81rNlvomiwed0V1YUxQdC1uOTg/view?resourcekey=0-2SNWq0CDAuWOBRRBL7ZZsw)) | 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] | -| **PACS** [[2]](https://openaccess.thecvf.com/content_ICCV_2017/papers/Li_Deeper_Broader_and_ICCV_2017_paper.pdf) ([1](https://drive.google.com/uc?id=1JFr8f805nMUelQWWmfnJR3y4_SYoN5Pd); or [original](https://drive.google.com/drive/folders/0B6x7gtvErXgfUU1WcGY5SzdwZVk?resourcekey=0-2fvpQY_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] | -| **DomainNet** [[33](https://openaccess.thecvf.com/content_ICCV_2019/papers/Peng_Moment_Matching_for_Multi-Source_Domain_Adaptation_ICCV_2019_paper.pdf)] ([clipart](http://csr.bu.edu/ftp/visda/2019/multi-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] | +| **OfficeHome** [[20]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Venkateswara_Deep_Hashing_Network_CVPR_2017_paper.pdf) ([1](https://drive.google.com/uc?id=1uY0pj7oFsjMxRwaD3Sxy0jgel0fsYXLC); or [original](https://drive.google.com/file/d/0B81rNlvomiwed0V1YUxQdC1uOTg/view?resourcekey=0-2SNWq0CDAuWOBRRBL7ZZsw)) | 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], [231] | +| **PACS** [[2]](https://openaccess.thecvf.com/content_ICCV_2017/papers/Li_Deeper_Broader_and_ICCV_2017_paper.pdf) ([1](https://drive.google.com/uc?id=1JFr8f805nMUelQWWmfnJR3y4_SYoN5Pd); or [original](https://drive.google.com/drive/folders/0B6x7gtvErXgfUU1WcGY5SzdwZVk?resourcekey=0-2fvpQY_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], [231] | +| **DomainNet** [[33](https://openaccess.thecvf.com/content_ICCV_2019/papers/Peng_Moment_Matching_for_Multi-Source_Domain_Adaptation_ICCV_2019_paper.pdf)] ([clipart](http://csr.bu.edu/ftp/visda/2019/multi-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], [231] | | **mini-DomainNet** [[34]](https://arxiv.53yu.com/pdf/2003.07325) | Object recognition; a smaller and less noisy version of DomainNet; 4 domains: {clipart, painting, real, sketch}; 140,006 samples | [34], [130], [156], [157], [210] | **ImageNet-Sketch** [[35]](https://arxiv.53yu.com/pdf/1903.06256) | Object recognition; 2 domains: {real, sketch}; 50,000 samples | [64] | **VisDA-17** [[36](https://arxiv.53yu.com/pdf/1710.06924)] | Object recognition; 3 domains of synthetic-to-real generalization; 280,157 samples | [119], [182] | @@ -497,7 +503,7 @@ If you would like to contribute to our repository or have any questions/advice, **SYNTHIA** [[42]](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.pdf) | Semantic segmentation; 15 domains with 4 locations and 5 weather conditions; 2,700 samples | [27], [62], [115], [141], [151], [185], [193] | **GTA5-Cityscapes** [[43]](https://linkspringer.53yu.com/chapter/10.1007/978-3-319-46475-6_7), [[44]](http://openaccess.thecvf.com/content_cvpr_2016/papers/Cordts_The_Cityscapes_Dataset_CVPR_2016_paper.pdf) | Semantic segmentation; 2 domains of synthetic-to-real generalization; 29,966 samples | [62], [115], [185], [193] | **Cityscapes-ACDC** [[44]](http://openaccess.thecvf.com/content_cvpr_2016/papers/Cordts_The_Cityscapes_Dataset_CVPR_2016_paper.pdf) ([original](https://acdc.vision.ee.ethz.ch/overview)) | Semantic segmentation; real life domain shifts, ACDC contains four different weather conditions: rain, fog, snow, night | [215] | -**Terra Incognita (TerraInc)** [[45]](http://openaccess.thecvf.com/content_ECCV_2018/papers/Beery_Recognition_in_Terra_ECCV_2018_paper.pdf) ([1](https://lilablobssc.blob.core.windows.net/caltechcameratraps/eccv_18_all_images_sm.tar.gz) and [2](https://lilablobssc.blob.core.windows.net/caltechcameratraps/labels/caltech_camera_traps.json.zip); or [original](https://lila.science/datasets/caltech-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] | +**Terra Incognita (TerraInc)** [[45]](http://openaccess.thecvf.com/content_ECCV_2018/papers/Beery_Recognition_in_Terra_ECCV_2018_paper.pdf) ([1](https://lilablobssc.blob.core.windows.net/caltechcameratraps/eccv_18_all_images_sm.tar.gz) and [2](https://lilablobssc.blob.core.windows.net/caltechcameratraps/labels/caltech_camera_traps.json.zip); or [original](https://lila.science/datasets/caltech-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], [231] | **Market-Duke** [[46]](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zheng_Scalable_Person_Re-Identification_ICCV_2015_paper.pdf), [[47]](https://linkspringer.53yu.com/chapter/10.1007/978-3-319-48881-3_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] |