CoChat
Sign Up
Cited by 1,315Domain Adaptation and Few-Shot LearningReinforcement Learning in RoboticsGenerative Adversarial Networks and Image Synthesis

Domain Generalization: A Survey

Open access
Zhou, Kaiyang, Liu, Ziwei, Qiao, Yu, Xiang, Tao, Loy, Chen Change·2022·IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI 10.1109/tpami.2022.3195549
Open this paper in CoChat — free accountOpen PDF

Abstract

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the i.i.d. assumption on source/target data, which is often violated in practice due to domain shift. Domain generalization (DG) aims to achieve OOD generalization by using only source data for model learning. Over the last ten years, research in DG has made great progress, leading to a broad spectrum of methodologies, e.g., those based on domain alignment, meta-learning, data augmentation, or ensemble learning, to name a few; DG has also been studied in various application areas including computer vision, speech recognition, natural language processing, medical imaging, and reinforcement learning. In this paper, for the first time a comprehensive literature review in DG is provided to summarize the developments over the past decade. Specifically, we first cover the background by formally defining DG and relating it to other relevant fields like domain adaptation and transfer learning. Then, we conduct a thorough review into existing methods and theories. Finally, we conclude this survey with insights and discussions on future research directions.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2022.3195549

Cites

23 of 23 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • DRL agents often fail to generalize well to environments only slightly different from those encountered during training.

    “DRL agents often fail to generalize well to environments only slightly different from those encountered during training [21, 63].”

    From Improving Environment Novelty Quantification for Effective Unsupervised Environment Design (2024) · cites this paper as [63]

    The survey’s reinforcement-learning discussion (p. 5) says agents trained in one environment often overfit and generalize poorly to unseen environments. It describes environmental changes but does not establish that this often happens when the differences are only slight. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 231

  1. [2]B. Recht, R. Roelofs, L. Schmidt, and V. Shankar, "Do imagenet classifiers generalize to imagenet?" in ICML, 2019.
  2. [4]R. Taori, A. Dave, V. Shankar, N. Carlini, B. Recht, and L. Schmidt, "Measuring robustness to natural distribution shifts in image classification," in NeurIPS, 2020.
  3. [5]G. Blanchard, A. A. Deshmukh, U. Dogan, G. Lee, and C. Scott, "Domain generalization by marginal transfer learning," JMLR, 2021.
  4. [7]A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classi- fication with deep convolutional neural networks," in NeurIPS, 2012.
  5. [10]J. Yang, K. Zhou, Y. Li, and Z. Liu, "Generalized out-of- distribution detection: A survey," arXiv preprint arXiv:2110.11334, 2021. · arXiv
  6. [11]J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "Imagenet: A large-scale hierarchical image database," in CVPR, 2009.
  7. [13]Z. Lu, Y. Yang, X. Zhu, C. Liu, Y.-Z. Song, and T. Xiang, "Stochas- tic classifiers for unsupervised domain adaptation," in CVPR, 2020.
  8. [14]K. Saito, K. Watanabe, Y. Ushiku, and T. Harada, "Maximum classifier discrepancy for unsupervised domain adaptation," in CVPR, 2018.
  9. [15]Y. Ganin and V. S. Lempitsky, "Unsupervised domain adaptation by backpropagation," in ICML, 2015.
  10. [16]M. Long, Y. Cao, J. Wang, and M. I. Jordan, "Learning transferable features with deep adaptation networks," in ICML, 2015.
  11. [17]Z. Liu, Z. Miao, X. Pan, X. Zhan, D. Lin, S. X. Yu, and B. Gong, "Open compound domain adaptation," in CVPR, 2020.
  12. [18]B. Li, Y. Wang, S. Zhang, D. Li, T. Darrell, K. Keutzer, and H. Zhao, "Learning invariant representations and risks for semi- supervised domain adaptation," in CVPR, 2021.
  13. [20]X. Yue, Y. Zhang, S. Zhao, A. Sangiovanni-Vincentelli, K. Keutzer, and B. Gong, "Domain randomization and pyramid consistency: Simulation-to-real generalization without accessing target do- main data," in ICCV, 2019.
  14. [21]R. Volpi, D. Larlus, and G. Rogez, "Continual adaptation of visual representations via domain randomization and meta-learning," in CVPR, 2021.
  15. [22]G. Blanchard, G. Lee, and C. Scott, "Generalizing from several re- lated classification tasks to a new unlabeled sample," in NeurIPS, 2011.
  16. [23]K. Zhou, Y. Yang, Y. Qiao, and T. Xiang, "Domain generalization with mixstyle," in ICLR, 2021.
  17. [24]X. Fan, Q. Wang, J. Ke, F. Yang, B. Gong, and M. Zhou, "Adversar- ially adaptive normalization for single domain generalization," in CVPR, 2021.
  18. [25]X. Zhang, P. Cui, R. Xu, L. Zhou, Y. He, and Z. Shen, "Deep stable learning for out-of-distribution generalization," in CVPR, 2021.
  19. [26]P. Pandey, M. Raman, S. Varambally, and P. AP, "Domain gener- alization via inference-time label-preserving target projections," in CVPR, 2021.
  20. [27]Y. Shu, Z. Cao, C. Wang, J. Wang, and M. Long, "Open do- main generalization with domain-augmented meta-learning," in CVPR, 2021.
  21. [28]K. Zhou, Y. Yang, Y. Qiao, and T. Xiang, "Mixstyle neu- ral networks for domain generalization and adaptation," arXiv:2107.02053, 2021. · arXiv
  22. [29]K. Zhou, C. C. Loy, and Z. Liu, "Semi-supervised do- main generalization with stochastic stylematch," arXiv preprint arXiv:2106.00592, 2021. · arXiv
  23. [30]J. Cha, S. Chun, K. Lee, H.-C. Cho, S. Park, Y. Lee, and S. Park, "Swad: Domain generalization by seeking flat minima," NeurIPS, 2021.
  24. [31]H. Li, S. Jialin Pan, S. Wang, and A. C. Kot, "Domain generaliza- tion with adversarial feature learning," in CVPR, 2018.
  25. [32]Y. Li, X. Tiana, M. Gong, Y. Liu, T. Liu, K. Zhang, and D. Tao, "Deep domain generalization via conditional invariant adversar- ial networks," in ECCV, 2018.
  26. [33]D. Li, Y. Yang, Y.-Z. Song, and T. M. Hospedales, "Learning to generalize: Meta-learning for domain generalization," in AAAI, 2018.
  27. [34]Y. Balaji, S. Sankaranarayanan, and R. Chellappa, "Metareg: Towards domain generalization using meta-regularization," in NeurIPS, 2018.
  28. [35]K. Zhou, Y. Yang, T. Hospedales, and T. Xiang, "Learning to generate novel domains for domain generalization," in ECCV, 2020.
  29. [36]K. Zhou, Y. Yang, T. M. Hospedales, and T. Xiang, "Deep domain- adversarial image generation for domain generalisation." in AAAI, 2020.
  30. [37]D. Li, Y. Yang, Y.-Z. Song, and T. M. Hospedales, "Deeper, broader and artier domain generalization," in ICCV, 2017.
  31. [38]Y. Li, Y. Yang, W. Zhou, and T. Hospedales, "Feature-critic net- works for heterogeneous domain generalization," in ICML, 2019.
  32. [39]R. Volpi and V. Murino, "Addressing model vulnerability to distributional shifts over image transformation sets," in ICCV, 2019.
  33. [40]S. Shankar, V. Piratla, S. Chakrabarti, S. Chaudhuri, P. Jyothi, and S. Sarawagi, "Generalizing across domains via cross-gradient training," in ICLR, 2018.
  34. [42]Q. Liu, Q. Dou, and P.-A. Heng, "Shape-aware meta-learning for generalizing prostate mri segmentation to unseen domains," in MICCAI, 2020.
  35. [44]L. Fei-Fei, R. Fergus, and P. Perona, "Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories," in CVPR-W, 2004.
  36. [45]B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman, "Labelme: a database and web-based tool for image annotation," IJCV, 2008.
  37. [46]A. Khosla, T. Zhou, T. Malisiewicz, A. Efros, and A. Torralba, "Undoing the damage of dataset bias," in ECCV, 2012.
  38. [47]D. Hendrycks, N. Mu, E. D. Cubuk, B. Zoph, J. Gilmer, and B. Lakshminarayanan, "Augmix: A simple data processing method to improve robustness and uncertainty," in ICLR, 2020.
  39. [48]Z. Tang, Y. Gao, Y. Zhu, Z. Zhang, M. Li, and D. Metaxas, "Selfnorm and crossnorm for out-of-distribution robustness," arXiv preprint arXiv:2102.02811, 2021. · arXiv
  40. [49]F. M. Carlucci, A. D'Innocente, S. Bucci, B. Caputo, and T. Tom- masi, "Domain generalization by solving jigsaw puzzles," in CVPR, 2019.
  41. [50]S. Bucci, A. D'Innocente, Y. Liao, F. M. Carlucci, B. Caputo, and T. Tommasi, "Self-supervised learning across domains," arXiv preprint arXiv:2007.12368, 2020. · arXiv
  42. [51]H. Wang, Z. He, Z. C. Lipton, and E. P. Xing, "Learning robust representations by projecting superficial statistics out," in ICLR, 2019.
  43. [52]Z. Huang, H. Wang, E. P. Xing, and D. Huang, "Self-challenging improves cross-domain generalization," in ECCV, 2020.
  44. [53]M. Ghifary, W. B. Kleijn, M. Zhang, and D. Balduzzi, "Domain generalization for object recognition with multi-task autoen- coders," in ICCV, 2015.
  45. [54]Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," in IEEE, 1998.
  46. [55]Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng, "Reading digits in natural images with unsupervised feature learning," in NeurIPS-W, 2011.
  47. [56]C. Fang, Y. Xu, and D. N. Rockmore, "Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias," in ICCV, 2013.
  48. [57]M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, "The pascal visual object classes (voc) challenge," IJCV, 2010.
  49. [58]J. Xiao, J. Hays, K. A. Ehinger, A. Oliva, and A. Torralba, "Sun database: Large-scale scene recognition from abbey to zoo," in CVPR, 2010.
  50. [59]H. Venkateswara, J. Eusebio, S. Chakraborty, and S. Pan- chanathan, "Deep hashing network for unsupervised domain adaptation," in CVPR, 2017.
  51. [60]X. Peng, Q. Bai, X. Xia, Z. Huang, K. Saenko, and B. Wang, "Mo- ment matching for multi-source domain adaptation," in ICCV, 2019.
  52. [61]K. Zhou, Y. Yang, Y. Qiao, and T. Xiang, "Domain adaptive ensemble learning," arXiv preprint arXiv:2003.07325, 2020. · arXiv
  53. [62]X. Peng, B. Usman, N. Kaushik, J. Hoffman, D. Wang, and K. Saenko, "Visda: The visual domain adaptation challenge," arXiv preprint arXiv:1710.06924, 2017. · arXiv
  54. [63]D. Hendrycks, S. Basart, N. Mu, S. Kadavath, F. Wang, E. Dorundo, R. Desai, T. Zhu, S. Parajuli, M. Guo et al., "The many faces of robustness: A critical analysis of out-of-distribution generalization," in ICCV, 2021.
  55. [64]D. Hendrycks, K. Zhao, S. Basart, J. Steinhardt, and D. Song, "Natural adversarial examples," in CVPR, 2021.
  56. [65]S. Beery, G. Van Horn, and P. Perona, "Recognition in terra incognita," in ECCV, 2018.
  57. [66]X. Zhang, L. Zhou, R. Xu, P. Cui, Z. Shen, and H. Liu, "Nico++: Towards better benchmarking for domain generalization," arXiv preprint arXiv:2204.08040, 2022. · arXiv
  58. [67]S.-A. Rebuffi, H. Bilen, and A. Vedaldi, "Learning multiple visual domains with residual adapters," in NeurIPS, 2017.
  59. [69]K. Soomro, A. R. Zamir, and M. Shah, "Ucf101: A dataset of 101 human actions classes from videos in the wild," arXiv preprint arXiv:1212.0402, 2012. · arXiv
  60. [71]Z. Yao, Y. Wang, X. Du, M. Long, and J. Wang, "Adversarial pyra- mid network for video domain generalization," arXiv preprint arXiv:1912.03716, 2019. · arXiv
  61. [73]R. Volpi, H. Namkoong, O. Sener, J. Duchi, V. Murino, and S. Savarese, "Generalizing to unseen domains via adversarial data augmentation," in NeurIPS, 2018.
  62. [74]S. R. Richter, V. Vineet, S. Roth, and V. Koltun, "Playing for data: Ground truth from computer games," in ECCV, 2016.
  63. [75]M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, "The cityscapes dataset for semantic urban scene understanding," in CVPR, 2016.
  64. [76]L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, "Scalable person re-identification: A benchmark," in ICCV, 2015.
  65. [77]E. Ristani, F. Solera, R. Zou, R. Cucchiara, and C. Tomasi, "Per- formance measures and a data set for multi-target, multi-camera tracking," in ECCV, 2016.
  66. [78]Y. Shi, X. Yu, K. Sohn, M. Chandraker, and A. K. Jain, "Towards universal representation learning for deep face recognition," in CVPR, 2020.
  67. [87]G. Christie, N. Fendley, J. Wilson, and R. Mukherjee, "Functional map of the world," in CVPR, 2018.
  68. [88]S. Beery, E. Cole, and A. Gjoka, "The iwildcam 2020 competition dataset," arXiv preprint arXiv:2004.10340, 2020. · arXiv
  69. [89]D. Mahajan, S. Tople, and A. Sharma, "Domain generalization using causal matching," in ICML, 2021.
  70. [90]X. Wang, Y. Peng, L. Lu, Z. Lu, M. Bagheri, and R. M. Summers, "Chestx-ray8: Hospital-scale chest x-ray database and bench- marks on weakly-supervised classification and localization of common thorax diseases," in CVPR, 2017.
  71. [91]J. Irvin, P. Rajpurkar, M. Ko, Y. Yu, S. Ciurea-Ilcus, C. Chute, H. Marklund, B. Haghgoo, R. Ball, K. Shpanskaya et al., "Chex- pert: A large chest radiograph dataset with uncertainty labels and expert comparison," in AAAI, 2019.
  72. [92]K. Cobbe, O. Klimov, C. Hesse, T. Kim, and J. Schulman, "Quan- tifying generalization in reinforcement learning," in ICML, 2019.
  73. [93]K. Cobbe, C. Hesse, J. Hilton, and J. Schulman, "Leveraging procedural generation to benchmark reinforcement learning," in ICML, 2020.
  74. [94]D. Li, J. Zhang, Y. Yang, C. Liu, Y.-Z. Song, and T. M. Hospedales, "Episodic training for domain generalization," in ICCV, 2019.
  75. [95]J. Hoffman, E. Tzeng, T. Park, J.-Y. Zhu, P. Isola, K. Saenko, A. Efros, and T. Darrell, "Cycada: Cycle-consistent adversarial domain adaptation," in ICML, 2018.
  76. [96]R. Gong, W. Li, Y. Chen, and L. Van Gool, "Dlow: Domain flow for adaptation and generalization," in CVPR, 2019.
  77. [97]Y. Sun, L. Zheng, Y. Li, Y. Yang, Q. Tian, and S. Wang, "Learning part-based convolutional features for person re-identification," TPAMI, 2019.
  78. [98]W. Li, X. Zhu, and S. Gong, "Scalable person re-identification by harmonious attention," IJCV, 2019.
  79. [99]T. Chen, S. Ding, J. Xie, Y. Yuan, W. Chen, Y. Yang, Z. Ren, and Z. Wang, "Abd-net: Attentive but diverse person re- identification," in ICCV, 2019.
  80. [100]K. Zhou, Y. Yang, A. Cavallaro, and T. Xiang, "Omni-scale feature learning for person re-identification," in ICCV, 2019.
  81. [101]X. Chang, T. M. Hospedales, and T. Xiang, "Multi-level factorisa- tion net for person re-identification," in CVPR, 2018.
  82. [102]K. Zhou, Y. Yang, A. Cavallaro, and T. Xiang, "Learning gener- alisable omni-scale representations for person re-identification," TPAMI, 2021.
  83. [103]Y. Zhao, Z. Zhong, F. Yang, Z. Luo, Y. Lin, S. Li, and N. Sebe, "Learning to generalize unseen domains via memory- based multi-source meta-learning for person re-identification," in CVPR, 2021.
  84. [104]S. Choi, T. Kim, M. Jeong, H. Park, and C. Kim, "Meta batch-instance normalization for generalizable person re- identification," arXiv preprint arXiv:2011.14670, 2020. · arXiv
  85. [105]Y. Taigman, M. Yang, M. Ranzato, and L. Wolf, "Deepface: Clos- ing the gap to human-level performance in face verification," in CVPR, 2014.
  86. [106]Y. Sun, X. Wang, and X. Tang, "Deep learning face representation from predicting 10,000 classes," in CVPR, 2014.
  87. [107]Y. Wen, K. Zhang, Z. Li, and Y. Qiao, "A discriminative feature learning approach for deep face recognition," in ECCV, 2016.
  88. [108]Y. Guo, L. Zhang, Y. Hu, X. He, and J. Gao, "Ms-celeb-1m: A dataset and benchmark for large-scale face recognition," in ECCV, 2016.
  89. [109]L. Wolf, T. Hassner, and I. Maoz, "Face recognition in uncon- strained videos with matched background similarity," in CVPR, 2011.
  90. [112]B. F. Klare, B. Klein, E. Taborsky, A. Blanton, J. Cheney, K. Allen, P. Grother, A. Mah, and A. K. Jain, "Pushing the frontiers of unconstrained face detection and recognition: Iarpa janus bench- mark a," in CVPR, 2015.
  91. [114]S. Sengupta, J.-C. Chen, C. Castillo, V. M. Patel, R. Chellappa, and D. W. Jacobs, "Frontal to profile face verification in the wild," in WACV, 2016.
  92. [115]I. Kemelmacher-Shlizerman, S. M. Seitz, D. Miller, and E. Brossard, "The megaface benchmark: 1 million faces for recog- nition at scale," in CVPR, 2016.
  93. [116]J. Yang, Z. Lei, and S. Z. Li, "Learn convolutional neural network for face anti-spoofing," arXiv preprint arXiv:1408.5601, 2014. · arXiv
  94. [117]R. Shao, X. Lan, J. Li, and P. C. Yuen, "Multi-adversarial discrim- inative deep domain generalization for face presentation attack detection," in CVPR, 2019.
  95. [118]Y. Shi, J. Seely, P. H. Torr, N. Siddharth, A. Hannun, N. Usunier, and G. Synnaeve, "Gradient matching for domain generaliza- tion," arXiv preprint arXiv:2104.09937, 2021. · arXiv
  96. [119]A. Robey, G. J. Pappas, and H. Hassani, "Model-based domain generalization," NeurIPS, 2021.
  97. [120]H. Yao, Y. Wang, S. Li, L. Zhang, W. Liang, J. Zou, and C. Finn, "Improving out-of-distribution robustness via selective augmen- tation," arXiv preprint arXiv:2201.00299, 2022. · arXiv
  98. [121]Q. Dou, D. C. Castro, K. Kamnitsas, and B. Glocker, "Domain generalization via model-agnostic learning of semantic features," in NeurIPS, 2019.
  99. [122]B. Mazoure, I. Kostrikov, O. Nachum, and J. Tompson, "Im- proving zero-shot generalization in offline reinforcement learn- ing using generalized similarity functions," arXiv preprint arXiv:2111.14629, 2021. · arXiv
  100. [123]N. Hansen and X. Wang, "Generalization in reinforcement learn- ing by soft data augmentation," in ICRA, 2021.
  101. [126]S. Sagawa, P. W. Koh, T. B. Hashimoto, and P. Liang, "Distri- butionally robust neural networks for group shifts: On the im- portance of regularization for worst-case generalization," arXiv preprint arXiv:1911.08731, 2019. · arXiv
  102. [127]D. Krueger, E. Caballero, J.-H. Jacobsen, A. Zhang, J. Binas, D. Zhang, R. Le Priol, and A. Courville, "Out-of-distribution generalization via risk extrapolation (rex)," in ICML, 2021.
  103. [128]I. Gulrajani and D. Lopez-Paz, "In search of lost domain general- ization," arXiv preprint arXiv:2007.01434, 2020. · arXiv
  104. [129]Y. Yang and T. Hospedales, "Deep multi-task representation learning: A tensor factorisation approach," in ICLR, 2017.
  105. [130]A. Mallya, D. Davis, and S. Lazebnik, "Piggyback: Adapting a single network to multiple tasks by learning to mask weights," in ECCV, 2018.
  106. [131]S. Liu, E. Johns, and A. J. Davison, "End-to-end multi-task learning with attention," in CVPR, 2019.
  107. [132]P. Guo, C.-Y. Lee, and D. Ulbricht, "Learning to branch for multi- task learning," in ICML, 2020.
  108. [133]X. Sun, R. Panda, R. Feris, and K. Saenko, "Adashare: Learning what to share for efficient deep multi-task learning," in NeurIPS, 2020.
  109. [134]S. Wang, L. Yu, C. Li, C.-W. Fu, and P.-A. Heng, "Learning from extrinsic and intrinsic supervisions for domain generalization," in ECCV, 2020.
  110. [135]I. Albuquerque, N. Naik, J. Li, N. Keskar, and R. Socher, "Im- proving out-of-distribution generalization via multi-task self- supervised pretraining," arXiv preprint arXiv:2003.13525, 2020. · arXiv
  111. [138]R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmenta- tion," in CVPR, 2014.
  112. [141]W. Chen, Z. Yu, Z. Wang, and A. Anandkumar, "Automated synthetic-to-real generalization," in ICML, 2020.
  113. [142]W. Chen, Z. Yu, S. D. Mello, S. Liu, J. M. Alvarez, Z. Wang, and A. Anandkumar, "Contrastive syn-to-real generalization," in ICLR, 2021.
  114. [143]C. H. Lampert, H. Nickisch, and S. Harmeling, "Attribute-based classification for zero-shot visual object categorization," TPAMI, 2014.
  115. [145]——, "Conditional prompt learning for vision-language models," in CVPR, 2022.
  116. [146]W.-L. Chao, S. Changpinyo, B. Gong, and F. Sha, "An empirical study and analysis of generalized zero-shot learning for object recognition in the wild," in ECCV, 2016.
  117. [147]M. Mancini, Z. Akata, E. Ricci, and B. Caputo, "Towards recog- nizing unseen categories in unseen domains," in ECCV, 2020.
  118. [148]Y. Xian, C. H. Lampert, B. Schiele, and Z. Akata, "Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly," TPAMI, 2018.
  119. [149]C. Gan, T. Yang, and B. Gong, "Learning attributes equals multi- source domain generalization," in CVPR, 2016.
  120. [150]B. Gong, Y. Shi, F. Sha, and K. Grauman, "Geodesic flow kernel for unsupervised domain adaptation," in CVPR, 2012.
  121. [151]M. Long, H. Zhu, J. Wang, and M. I. Jordan, "Unsupervised domain adaptation with residual transfer networks," in NeurIPS, 2016.
  122. [152]Y. Balaji, R. Chellappa, and S. Feizi, "Normalized wasserstein for mixture distributions with applications in adversarial learning and domain adaptation," in ICCV, 2019.
  123. [153]G. Kang, L. Jiang, Y. Yang, and A. G. Hauptmann, "Contrastive adaptation network for unsupervised domain adaptation," in CVPR, 2019.
  124. [154]B. Kulis, K. Saenko, and T. Darrell, "What you saw is not what you get: Domain adaptation using asymmetric kernel trans- forms," in CVPR, 2011.
  125. [155]K.-C. Peng, Z. Wu, and J. Ernst, "Zero-shot deep domain adapta- tion," in ECCV, 2018.
  126. [156]P. Panareda Busto and J. Gall, "Open set domain adaptation," in ICCV, 2017.
  127. [157]Z. Cao, L. Ma, M. Long, and J. Wang, "Partial adversarial domain adaptation," in ECCV, 2018.
  128. [158]K. You, M. Long, Z. Cao, J. Wang, and M. I. Jordan, "Universal domain adaptation," in CVPR, 2019.
  129. [159]D. Wang, E. Shelhamer, S. Liu, B. Olshausen, and T. Darrell, "Tent: Fully test-time adaptation by entropy minimization," arXiv preprint arXiv:2006.10726, 2020. · arXiv
  130. [160]J. N. Kundu, N. Venkat, R. V. Babu et al., "Universal source-free domain adaptation," in CVPR, 2020.
  131. [161]M. Zhang, S. Levine, and C. Finn, "Memo: Test time ro- bustness via adaptation and augmentation," arXiv preprint arXiv:2110.09506, 2021. · arXiv
  132. [162]Y. Iwasawa and Y. Matsuo, "Test-time classifier adjustment mod- ule for model-agnostic domain generalization," NeurIPS, 2021.
  133. [163]Y. Sun, X. Wang, Z. Liu, J. Miller, A. Efros, and M. Hardt, "Test-time training with self-supervision for generalization under distribution shifts," in ICML, 2020.
  134. [164]S. Erfani, M. Baktashmotlagh, M. Moshtaghi, X. Nguyen, C. Leckie, J. Bailey, and R. Kotagiri, "Robust domain generali- sation by enforcing distribution invariance," in IJCAI, 2016.
  135. [165]M. Ghifary, D. Balduzzi, W. B. Kleijn, and M. Zhang, "Scatter component analysis: A unified framework for domain adaptation and domain generalization," TPAMI, 2017.
  136. [166]Y. Li, M. Gong, X. Tian, T. Liu, and D. Tao, "Domain generaliza- tion via conditional invariant representations," in AAAI, 2018.
  137. [167]X. Jin, C. Lan, W. Zeng, and Z. Chen, "Feature alignment and restoration for domain generalization and adaptation," arXiv preprint arXiv:2006.12009, 2020. · arXiv
  138. [168]S. Hu, K. Zhang, Z. Chen, and L. Chan, "Domain generalization via multidomain discriminant analysis," in UAI, 2020.
  139. [169]S. Motiian, M. Piccirilli, D. A. Adjeroh, and G. Doretto, "Uni- fied deep supervised domain adaptation and generalization," in ICCV, 2017.
  140. [170]C. Yoon, G. Hamarneh, and R. Garbi, "Generalizable feature learning in the presence of data bias and domain class imbalance with application to skin lesion classification," in MICCAI, 2019.
  141. [171]D. Mahajan, S. Tople, and A. Sharma, "Domain generalization using causal matching," arXiv preprint arXiv:2006.07500, 2020. · arXiv
  142. [172]Z. Wang, M. Loog, and J. van Gemert, "Respecting domain re- lations: Hypothesis invariance for domain generalization," arXiv preprint arXiv:2010.07591, 2020. · arXiv
  143. [173]H. Li, Y. Wang, R. Wan, S. Wang, T.-Q. Li, and A. C. Kot, "Domain generalization for medical imaging classification with linear-dependency regularization," in NeurIPS, 2020.
  144. [175]I. Albuquerque, J. Monteiro, M. Darvishi, T. H. Falk, and I. Mitliagkas, "Generalizing to unseen domains via distribution matching," arXiv preprint arXiv:1911.00804, 2019. · arXiv
  145. [176]Z. Deng, F. Ding, C. Dwork, R. Hong, G. Parmigiani, P. Patil, and P. Sur, "Representation via representations: Domain generaliza- tion via adversarially learned invariant representations," arXiv preprint arXiv:2006.11478, 2020. · arXiv
  146. [177]T. Matsuura and T. Harada, "Domain generalization using a mixture of multiple latent domains," in AAAI, 2020.
  147. [178]Y. Jia, J. Zhang, S. Shan, and X. Chen, "Single-side domain generalization for face anti-spoofing," in CVPR, 2020.
  148. [181]S. Zhao, M. Gong, T. Liu, H. Fu, and D. Tao, "Domain general- ization via entropy regularization," in NeurIPS, 2020.
  149. [182]D. Li, Y. Yang, Y.-Z. Song, and T. Hospedales, "Sequential learn- ing for domain generalization," in ECCV-W, 2020.
  150. [183]Y. Du, J. Xu, H. Xiong, Q. Qiu, X. Zhen, C. G. Snoek, and L. Shao, "Learning to learn with variational information bottleneck for domain generalization," in ECCV, 2020.
  151. [184]Y. Du, X. Zhen, L. Shao, and C. G. M. Snoek, "Metanorm: Learn- ing to normalize few-shot batches across domains," in ICLR, 2021.
  152. [185]B. Wang, M. Lapata, and I. Titov, "Meta-learning for domain gen- eralization in semantic parsing," arXiv preprint arXiv:2010.11988, 2020. · arXiv
  153. [189]F. Qiao, L. Zhao, and X. Peng, "Learning to learn single domain generalization," in CVPR, 2020.
  154. [190]A. Sinha, H. Namkoong, R. Volpi, and J. Duchi, "Certifying some distributional robustness with principled adversarial training," arXiv preprint arXiv:1710.10571, 2017. · arXiv
  155. [191]Z. Xu, D. Liu, J. Yang, C. Raffel, and M. Niethammer, "Robust and generalizable visual representation learning via random convolutions," in ICLR, 2021.
  156. [192]N. Somavarapu, C.-Y. Ma, and Z. Kira, "Frustratingly simple domain generalization via image stylization," arXiv preprint arXiv:2006.11207, 2020. · arXiv
  157. [193]F. C. Borlino, A. D'Innocente, and T. Tommasi, "Rethinking do- main generalization baselines," arXiv preprint arXiv:2101.09060, 2021. · arXiv
  158. [194]F. M. Carlucci, P. Russo, T. Tommasi, and B. Caputo, "Hallucinat- ing agnostic images to generalize across domains." in ICCV-W, 2019.
  159. [195]Z. Xu, W. Li, L. Niu, and D. Xu, "Exploiting low-rank structure from latent domains for domain generalization," in ECCV, 2014.
  160. [196]L. Niu, W. Li, and D. Xu, "Multi-view domain generalization for visual recognition," in ICCV, 2015.
  161. [197]——, "Visual recognition by learning from web data: A weakly supervised domain generalization approach," in CVPR, 2015.
  162. [202]S. Seo, Y. Suh, D. Kim, J. Han, and B. Han, "Learning to optimize domain specific normalization for domain generalization," in ECCV, 2020.
  163. [203]M. Segù, A. Tonioni, and F. Tombari, "Batch normalization embeddings for deep domain generalization," arXiv preprint arXiv:2011.12672, 2020. · arXiv
  164. [205]J. Cha, H. Cho, K. Lee, S. Park, Y. Lee, and S. Park, "Domain generalization needs stochastic weight averaging for robustness on domain shifts," arXiv preprint arXiv:2102.08604, 2021. · arXiv
  165. [206]U. Maniyar, A. A. Deshmukh, U. Dogan, and V. N. Balasubrama- nian, "Zero shot domain generalization," in BMVC, 2020.
  166. [207]P. Chattopadhyay, Y. Balaji, and J. Hoffman, "Learning to balance specificity and invariance for in and out of domain generaliza- tion," in ECCV, 2020.
  167. [208]V. Piratla, P. Netrapalli, and S. Sarawagi, "Efficient domain generalization via common-specific low-rank decomposition," in ICML, 2020.
  168. [209]M. Ilse, J. M. Tomczak, C. Louizos, and M. Welling, "Diva: Domain invariant variational autoencoder," in ICLR-W, 2019.
  169. [210]G. Wang, H. Han, S. Shan, and X. Chen, "Cross-domain face presentation attack detection via multi-domain disentangled rep- resentation learning," in CVPR, 2020.
  170. [211]M. Laskin, K. Lee, A. Stooke, L. Pinto, P. Abbeel, and A. Srinivas, "Reinforcement learning with augmented data," NeurIPS, 2020.
  171. [212]I. Kostrikov, D. Yarats, and R. Fergus, "Image augmentation is all you need: Regularizing deep reinforcement learning from pixels," arXiv preprint arXiv:2004.13649, 2020. · arXiv
  172. [214]K. Lee, K. Lee, J. Shin, and H. Lee, "Network randomization: A simple technique for generalization in deep reinforcement learning," arXiv preprint arXiv:1910.05396, 2019. · arXiv
  173. [215]D. Yarats, A. Zhang, I. Kostrikov, B. Amos, J. Pineau, and R. Fer- gus, "Improving sample efficiency in model-free reinforcement learning from images," in AAAI, 2021.
  174. [216]M. Laskin, A. Srinivas, and P. Abbeel, "Curl: Contrastive unsu- pervised representations for reinforcement learning," in ICML, 2020.
  175. [217]C. Villani, Optimal transport: old and new. Springer Science & Business Media, 2008.
  176. [218]B. Schölkopf, D. Janzing, J. Peters, E. Sgouritsa, K. Zhang, and J. Mooij, "On causal and anticausal learning," in ICML, 2012.
  177. [219]A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Schölkopf, and A. Smola, "A kernel two-sample test," JMLR, 2012.
  178. [220]I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde- Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adver- sarial nets," in NeurIPS, 2014.
  179. [222]W. Zhang, W. Ouyang, W. Li, and D. Xu, "Collaborative and adversarial network for unsupervised domain adaptation," in CVPR, 2018.
  180. [223]M. Long, Z. Cao, J. Wang, and M. I. Jordan, "Conditional adver- sarial domain adaptation," in NeurIPS, 2018.
  181. [224]C.-Y. Lee, T. Batra, M. H. Baig, and D. Ulbricht, "Sliced wasser- stein discrepancy for unsupervised domain adaptation," in CVPR, 2019.
  182. [225]Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. Lempitsky, "Domain- adversarial training of neural networks," JMLR, 2016.
  183. [226]C. Finn, P. Abbeel, and S. Levine, "Model-agnostic meta-learning for fast adaptation of deep networks," in ICML, 2017.
  184. [227]T. Hospedales, A. Antoniou, P. Micaelli, and A. Storkey, "Meta-learning in neural networks: A survey," arXiv preprint arXiv:2004.05439, 2020. · arXiv
  185. [228]J.-M. Perez-Rua, X. Zhu, T. M. Hospedales, and T. Xiang, "Incre- mental few-shot object detection," in CVPR, 2020.
  186. [229]J. Gordon, J. Bronskill, M. Bauer, S. Nowozin, and R. E. Turner, "Meta-learning probabilistic inference for prediction," in ICLR, 2019.
  187. [230]I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
  188. [232]C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. J. Goodfellow, and R. Fergus, "Intriguing properties of neural net- works," in ICLR, 2014.
  189. [233]X. Huang and S. Belongie, "Arbitrary style transfer in real-time with adaptive instance normalization," in ICCV, 2017.
  190. [234]H. Zhang, M. Cisse, Y. N. Dauphin, and D. Lopez-Paz, "mixup: Beyond empirical risk minimization," in ICLR, 2018.
  191. [236]C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions," in CVPR, 2015.
  192. [237]T. Malisiewicz, A. Gupta, and A. A. Efros, "Ensemble of exemplar-svms for object detection and beyond," in ICCV, 2011.
  193. [239]P. Izmailov, D. Podoprikhin, T. Garipov, D. Vetrov, and A. G. Wilson, "Averaging weights leads to wider optima and better generalization," in UAI, 2018.
  194. [240]M. Noroozi and P. Favaro, "Unsupervised learning of visual representations by solving jigsaw puzzles," in ECCV, 2016.
  195. [241]S. Gidaris, P. Singh, and N. Komodakis, "Unsupervised represen- tation learning by predicting image rotations," in ICLR, 2018.
  196. [242]L. Jing and Y. Tian, "Self-supervised visual feature learning with deep neural networks: A survey," TPAMI, 2020.
  197. [243]M. Caron, P. Bojanowski, A. Joulin, and M. Douze, "Deep clus- tering for unsupervised learning of visual features," in ECCV, 2018.
  198. [244]K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, "Momentum con- trast for unsupervised visual representation learning," in CVPR, 2020.
  199. [245]J.-B. Grill, F. Strub, F. Altché, C. Tallec, P. H. Richemond, E. Buchatskaya, C. Doersch, B. A. Pires, Z. D. Guo, M. G. Azar et al., "Bootstrap your own latent: A new approach to self- supervised learning," in NeurIPS, 2020.
  200. [246]X. Chen, Y. Duan, R. Houthooft, J. Schulman, I. Sutskever, and P. Abbeel, "Infogan: Interpretable representation learning by information maximizing generative adversarial nets," in NeurIPS, 2016.

200 of 231 shown

Cited by

Sorted by citations

Authors
Zhou, K., Liu, Z., Qiao, Y., Xiang, T., & Loy, C. C.
Affiliations
  • Nanyang Technological University (SG)
  • Chinese Academy of Sciences (CN)
  • University of Surrey (GB)
ORCID
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2022
Volume
45
Issue
4
Pages
1-20
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
DOI
10.1109/tpami.2022.3195549
OpenAlex
W4289639938
Cited by
1,315
References
23
Citations by year
2026: 215 · 2025: 367 · 2024: 392 · 2023: 226 · 2022: 86 · 2021: 28 · 2020: 1
FWCI
83.53
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • DR-NTU (Nanyang Technological University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Natural Science Foundation of China (61876176, U1713208, 2020YFC2004800)
  • Chinese Academy of Sciences (KFJ-STS-QYZX-092)
  • Ministry of Education, India
  • National Key Research and Development Program of China (U1713208, 2020YFC2004800)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
Keywords
domain generalization, out-of-distribution generalization, domain shift, domain adaptation, transfer learning, domain alignment, meta-learning, data augmentation, ensemble learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review