Abstract
Convolutional neural networks (CNN) have demonstrated remarkable performance, when the training and testing data are from the same distribution. However, such trained CNN models often largely degrade on testing data which is unseen and Out-Of-the-Distribution (OOD). To address this issue, we propose a novel “Decoupled-Mixup" method to train CNN models for OOD visual recognition. Different from previous work combining pairs of images homogeneously, our method decouples each image into discriminative and noise-prone regions, and then heterogeneously combine these regions of image pairs to train CNN models. Since the observation is that noise-prone regions such as textural and clutter background are adverse to the generalization ability of CNN models during training, we enhance features from discriminative regions and suppress noise-prone ones when combining an image pair. To further improves the generalization ability of trained models, we propose to disentangle discriminative and noise-prone regions in frequency-based and context-based fashions. Experiment results show the high generalization performance of our method on testing data that are composed of unseen contexts, where our method achieves 85.76% top-1 accuracy in Track-1 and 79.92% in Track-2 in NICO Challenge. The source code is available at https://github.com/HaozheLiu-ST/NICOChallenge-OOD-Classification.
H. Liu, W. Zhang and J. Xie—Equal Contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)
Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414–2423 (2016)
Guo, H., Mao, Y., Zhang, R.: Mixup as locally linear out-of-manifold regularization. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 33, pp. 3714–3722 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: AugMix: A simple data processing method to improve robustness and uncertainty. Proceedings of the International Conference on Learning Representations (ICLR) (2020)
Hong, M., Choi, J., Kim, G.: Stylemix: Separating content and style for enhanced data augmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14862–14870 (2021)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501–1510 (2017)
Kim, J.H., Choo, W., Song, H.O.: Puzzle mix: Exploiting saliency and local statistics for optimal mixup. In: International Conference on Machine Learning, pp. 5275–5285. PMLR (2020)
Liu, F., Liu, H., Zhang, W., Liu, G., Shen, L.: One-class fingerprint presentation attack detection using auto-encoder network. IEEE Trans. Image Process. 30, 2394–2407 (2021)
Liu, H., et al.: Robust representation via dynamic feature aggregation. arXiv preprint arXiv:2205.07466 (2022)
Liu, H., Wu, H., Xie, W., Liu, F., Shen, L.: Group-wise inhibition based feature regularization for robust classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 478–486 (2021)
Liu, H., Zhang, W., Liu, F., Wu, H., Shen, L.: Fingerprint presentation attack detector using global-local model. IEEE Transactions on Cybernetics (2021)
Paszke, A., et al.: Pytorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Piratla, V., Netrapalli, P., Sarawagi, S.: Efficient domain generalization via common-specific low-rank decomposition. In: International Conference on Machine Learning, pp. 7728–7738. PMLR (2020)
Verma, V., et al.: Manifold mixup: Better representations by interpolating hidden states. In: International Conference on Machine Learning, pp. 6438–6447. PMLR (2019)
Xie, J., Hou, X., Ye, K., Shen, L.: CLIMS: Cross language image matching for weakly supervised semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4483–4492 (June 2022)
Xie, J., Luo, C., Zhu, X., Jin, Z., Lu, W., Shen, L.: Online refinement of low-level feature based activation map for weakly supervised object localization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 132–141 (October 2021)
Xie, J., Xiang, J., Chen, J., Hou, X., Zhao, X., Shen, L.: C2AM: Contrastive learning of class-agnostic activation map for weakly supervised object localization and semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 989–998 (2022)
Xu, Q., Zhang, R., Zhang, Y., Wang, Y., Tian, Q.: A fourier-based framework for domain generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14383–14392 (2021)
Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6023–6032 (2019)
Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
Zhang, L., Deng, Z., Kawaguchi, K., Ghorbani, A., Zou, J.: How does mixup help with robustness and generalization? ICLR (2021)
Zhang, W., Liu, H., Liu, F., Ramachandra, R., Busch, C.: Frt-pad: Effective presentation attack detection driven by face related task. arXiv preprint arXiv:2111.11046 (2021)
Zhang, X., Cui, P., Xu, R., Zhou, L., He, Y., Shen, Z.: Deep stable learning for out-of-distribution generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5372–5382 (2021)
Zhang, X., et al.: Towards domain generalization in object detection. arXiv preprint arXiv:2203.14387 (2022)
Zhang, X., Zhou, L., Xu, R., Cui, P., Shen, Z., Liu, H.: Nico++: Towards better benchmarking for domain generalization. arXiv preprint arXiv:2204.08040 (2022)
Zhang, X., Zhou, L., Xu, R., Cui, P., Shen, Z., Liu, H.: Towards unsupervised domain generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4910–4920 (2022)
Zhou, K., Yang, Y., Hospedales, T., Xiang, T.: Deep domain-adversarial image generation for domain generalisation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13025–13032 (2020)
Zhou, K., Yang, Y., Hospedales, T., Xiang, T.: Learning to generate novel domains for domain generalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 561–578. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_33
Zhou, K., Yang, Y., Qiao, Y., Xiang, T.: Domain generalization with mixstyle. ICLR (2021)
Acknowledgements
We would like to thank the efforts of the NICO Challenge officials, who are committed to maintaining the fairness and openness of the competition. We also could not have undertaken this paper without efforts of every authors. This work was supported in part by the Key-Area Research and Development Program of Guangdong Province, China (No. 2018B010111001), National Key R &D Program of China (2018YFC2000702), in part by the Scientific and Technical Innovation 2030-“New Generation Artificial Intelligence" Project (No. 2020AAA0104100) and in part by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research through the Visual Computing Center (VCC) funding.
Author information
Authors and Affiliations
Contributions
Haozhe Liu , Wentian Zhang , Jinheng Xie : Equal Contribution
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, H. et al. (2023). Decoupled Mixup for Out-of-Distribution Visual Recognition. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13806. Springer, Cham. https://doi.org/10.1007/978-3-031-25075-0_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-25075-0_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25074-3
Online ISBN: 978-3-031-25075-0
eBook Packages: Computer ScienceComputer Science (R0)