Abstract
Domain generalization aims to learn a model that is generalizable to an unseen target domain, which is a fundamental and challenging task in machine learning for out-of-distribution generalization. This paper proposes a novel domain generalization approach that enforces the learned model to be able to generalize well over the train/val subset splitting of the training dataset. This idea is modeled herein as an adversarial data splitting framework, formulated as a min-max optimization problem inspired by the meta-learning approach. The min-max optimization problem is solved by iteratively splitting the training dataset into the training and val subsets to maximize the domain shift measured by the objective function and updating the model parameters to enable the model to generalize well from the training subset to the val subset by minimizing the objective function. This adversarial training approach does not assume the known domain labels of the training data; instead, it automatically investigates the “hard” splitting of the train/val subsets to learn the generalizable model. Extensive experimental results using three benchmark datasets demonstrate the superiority of this approach. In addition, we derive a generalization error bound for the theoretical understanding of our proposed approach.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, 2012
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. ArXiv:1409.1556
Torralba A, Efros A A. Unbiased look at dataset bias. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011
Pan S J, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng, 2010, 22: 1345–1359
Blanchard G, Lee G, Scott C. Generalizing from several related classification tasks to a new unlabeled sample. In: Proceedings of Advances in Neural Information Processing Systems, 2011
Muandet K, Balduzzi D, Schölkopf B. Domain generalization via invariant feature representation. In: Proceedings of Advances in Neural Information Processing Systems, 2013
Ganin Y, Ustinova E, Ajakan H, et al. Domain-adversarial training of neural networks. J Mach Learn Res, 2016, 17: 2096–2030
Long M S, Cao Y, Wang J M, et al. Learning transferable features with deep adaptation networks. In: Proceedings of International Conference on International Conference on Machine Learning, 2015
Tao J W, Chung F L, Wang S T. A kernel learning framework for domain adaptation learning. Sci China Inf Sci, 2012, 55: 1983–2007
Wang Y, Peng J J, Wang H B, et al. Progressive learning with multi-scale attention network for cross-domain vehicle reidentification. Sci China Inf Sci, 2022, 65: 160103
Huang L Q, Liu Z G, Pan Q, et al. Evidential combination of augmented multi-source of information based on domain adaptation. Sci China Inf Sci, 2020, 63: 210203
Hoffman J, Tzeng E, Park T, et al. CyCADA: cycle-consistent adversarial domain adaptation. In: Proceedings of International Conference on International Conference on Machine Learning, 2018
Li H L, Pan S J, Wang S Q, et al. Domain generalization with adversarial feature learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Zhao S S, Gong M M, Liu T L, et al. Domain generalization via entropy regularization. In: Proceedings of Advances in Neural Information Processing Systems, 2020
Balaji Y, Sankaranarayanan S, Chellappa R. Metareg: towards domain generalization using meta-regularization. In: Proceedings of Advances in Neural Information Processing Systems, 2018
Dou Q, de Castro D C, Kamnitsas K, et al. Domain generalization via model-agnostic learning of semantic features. In: Proceedings of Advances in Neural Information Processing Systems, 2019
Li D, Yang Y X, Song Y Z, et al. Learning to generalize: meta-learning for domain generalization. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligenc, 2018
Li Y Y, Yang Y X, Zhou W, et al. Feature-critic networks for heterogeneous domain generalization. In: Proceedings of International Conference on Machine Learning, 2019
Zhou K Y, Yang Y X, Hospedales T M, et al. Deep domain-adversarial image generation for domain generalisation. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020
Zhou K Y, Yang Y X, Qiao Y, et al. Domain generalization with mixstyle. In: Proceedings of International Conference on Learning Representations, 2021
Xu Q W, Zhang R P, Zhang Y, et al. A fourier-based framework for domain generalization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Carlucci F M, D’Innocente A, Bucci S, et al. Domain generalization by solving jigsaw puzzles. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Matsuura T, Harada T. Domain generalization using a mixture of multiple latent domains. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020
Huang Z Y, Wang H H, Xing E P, et al. Self-challenging improves cross-domain generalization. In: Proceedings of European Conference on Computer Vision, 2020
Pandey P, Raman M, Varambally S, et al. Generalization on unseen domains via inference-time label-preserving target projections. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Ghifary M, Kleijn W B, Zhang M, et al. Domain generalization for object recognition with multi-task autoencoders. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2015
Piratla V, Netrapalli P, Sarawagi S. Efficient domain generalization via common-specific low-rank decomposition. In: Proceedings of International Conference on International Conference on Machine Learning, 2020
Meng R, Li X F, Chen W J, et al. Attention diversification for domain generalization. In: Proceedings of European Conference on Computer Vision, 2022
Du Y J, Xu J, Xiong H, et al. Learning to learn with variational information bottleneck for domain generalization. In: Proceedings of European Conference on Computer Vision, 2020
Du Y, Xu J, Xiong H, et al. Learning to optimize domain specific normalization for domain generalization. In: Proceedings of European Conference on Computer Vision, 2020
Li D, Zhang J S, Yang Y X, et al. Episodic training for domain generalization. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019
Wang H, He Z, Lipton Z C, et al. Learning robust representations by projecting superficial statistics out. In: Proceedings of International Conference on Learning Representations, 2019
Qiao F C, Zhao L, Peng X. Learning to learn single domain generalization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Volpi R, Namkoong H, Sener O, et al. Generalizing to unseen domains via adversarial data augmentation. In: Proceedings of Advances in Neural Information Processing Systems, 2018
Xiao N, Zhang L. Dynamic weighted learning for unsupervised domain adaptation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. 15242–15251
Shi W X, Zhang L, Chen W J, et al. Universal domain adaptive object detector. In: Proceedings of the 30th ACM International Conference on Multimedia, 2022. 2258–2266
He Z W, Zhang L, Yang Y, et al. Partial alignment for object detection in the wild. IEEE Trans Circ Syst Video Technol, 2022, 32: 5238–5251
Goodfellow I J, Shlens J, Szegedy C. Explaining and harnessing adversarial examples. In: Proceedings of International Conference on Learning Representations, 2015
Nguyen A, Yosinski J, Clune J. Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
Madry A, Makelov A, Schmidt L, et al. Towards deep learning models resistant to adversarial attacks. In: Proceedings of International Conference on Learning Representations, 2018
Wang H, Wang Y T, Zhou Z, et al. CosFace: large margin cosine loss for deep face recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Fan Y, Tian F, Qin T, et al. Learning to teach. In: Proceedings of International Conference on Learning Representations, 2018
Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of International Conference on International Conference on Machine Learning, 2017
Sun J, Tappen M F. Learning non-local range Markov random field for image restoration. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011
Ben-David S, Blitzer J, Crammer K, et al. Analysis of representations for domain adaptation. In: Proceedings of Advances in Neural Information Processing Systems, 2007
Ben-David S, Blitzer J, Crammer K, et al. A theory of learning from different domains. Mach Learn, 2010, 79: 151–175
Saito K, Kim D, Sclaroff S, et al. Semi-supervised domain adaptation via minimax entropy. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019
Li D, Yang Y X, Song Y Z, et al. Deeper, broader and artier domain generalization. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017
Venkateswara H, Eusebio J, Chakraborty S, et al. Deep hashing network for unsupervised domain adaptation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Krizhevsky A, Hinton G. Learning Multiple Layers of Features from Tiny Images. Technical report, 2009
D’Innocente A, Caputo B. Domain generalization with domain-specific aggregation modules. In: Proceedings of German Conference on Pattern Recognition, 2018
Zhou K, Yang Y, Hospedales T, et al. Learning to generate novel domains for domain generalization. In: Proceedings of European Conference on Computer Vision, 2020
Huang J X, Guan D Y, Xiao A R, et al. FSDR: frequency space domain randomization for domain generalization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Nam H, Lee H, Park J, et al. Reducing domain gap via style-agnostic networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Zhang Y B, Li M H, Li R H, et al. Exact feature distribution matching for arbitrary style transfer and domain generalization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Yao X F, Bai Y, Zhang X Y, et al. PCL: proxy-based contrastive learning for domain generalization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Chen C Q, Tang L Y, Liu F, et al. Mix and reason: reasoning over semantic topology with data mixing for domain generalization. In: Proceedings of Advances in Neural Information Processing Systems, 2022
Wang X, Saxon M, Li J, et al. Causal balancing for domain generalization. In: Proceedings of International Conference on Learning Representations, 2023
Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis, 2015, 115: 211–252
Gu X, Sun J, Xu Z B. Spherical space domain adaptation with robust pseudo-label loss. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Cubuk E D, Zoph B, Shlens J, et al. Randaugment: practical automated data augmentation with a reduced search space. In: Proceedings of Advances in Neural Information Processing Systems, 2020
Hendrycks D, Dietterich T. Benchmarking neural network robustness to common corruptions and perturbations. In: Proceedings of International Conference on Learning Representations, 2019
van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res, 2008, 9: 2579–2605
Acknowledgements
This work was supported by National Key R&D Program of China (Grant No. 2021YFA1003002), National Natural Science Foundation of China (Grant Nos. U20B2075, 12125104, 11971373, 61721002), and Fundamental Research Funds for the Central Universities.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supporting information Appendixes A–D. The supporting information is available online at https://info.scichina.com and https://link.springer.com. The supporting materials are published as submitted, without typesetting or editing. The responsibility for scientific accuracy and content remains entirely with the authors.
Supplementary File
Rights and permissions
About this article
Cite this article
Gu, X., Sun, J. & Xu, Z. Adversarial data splitting for domain generalization. Sci. China Inf. Sci. 67, 152101 (2024). https://doi.org/10.1007/s11432-022-3857-5
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-022-3857-5