Abstract
Deep models have demonstrated outstanding ability in various computer vision tasks but are also notoriously known to generalize poorly when encountering unseen domains with different statistics. To alleviate this issue, in this technical report we present a new domain generalization method based on training sample mixup. The main enabling factor of our superior performance lies in the global mixup strategy across the source domains, where the batched samples from multiple graphic devices are mixed up for a better generalization ability. Since the domain gap in NICO datasets is mainly due to the intertwined background bias, the global mix strategy decreases such gap to a great extent by producing abundant mixed backgrounds. Besides, we have conducted extensive experiments on different backbones combined with various data augmentation to study the generalization performance of different model structures. Our final ensembled model achieved 74.07% on the test set and took the 3rd place according to the image classification accuracy (Acc.) in NICO Common Context Generalization Challenge 2022.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT’2010, pp. 177–186. Springe, Chamr (2010). https://doi.org/10.1007/978-3-7908-2604-3_16
Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop,. pp. 702–703 (2020)
Dou, Q., Coelho de Castro, D., Kamnitsas, K., Glocker, B.: Domain generalization via model-agnostic learning of semantic features. In: 32nd Proceedings on Advances in Neural Information Processing Systems (2019)
Fu, Y., et al.: Partial feature selection and alignment for multi-source domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2021)
Gong, R., Li, W., Chen, Y., Dai, D., Van Gool, L.: DLOW: domain flow and applications. Int. J. CardioVasc .Imaging 129(10), 2865–2888 (2021)
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)
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)
Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.: Averaging weights leads to wider optima and better generalization. In: 34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018 (2018)
Kang, G., Jiang, L., Wei, Y., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for single-and multi-source domain adaptation. IEEE trans. Pattern Anal. Mach. Intell. 44, 1793–1804 (2020)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: 25th Proceedings on Advances in Neural Information Processing Systems (2012)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: 25th Advances in Neural Information Processing Systems: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held 3–6 December 2012, Lake Tahoe, Nevada, United States, pp. 1106–1114 (2012)
Li, D., Zhang, J., Yang, Y., Liu, C., Song, Y.Z., Hospedales, T.M.: Episodic training for domain generalization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1446–1455 (2019)
Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976–11986 (2022)
Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: ICML, pp. 97–105 (2015)
Lu, Y., Luo, Y., Zhang, L., Li, Z., Yang, Y., Xiao, J.: Bidirectional self-training with multiple anisotropic prototypes for domain adaptive semantic segmentation. arXiv preprint arXiv:2204.07730 (2022)
Luo, Y., Liu, P., Guan, T., Yu, J., Yang, Y.: Significance-aware information bottleneck for domain adaptive semantic segmentation. In: ICCV, pp. 6778–6787 (2019)
Luo, Y., Liu, P., Guan, T., Yu, J., Yang, Y.: Adversarial style mining for one-shot unsupervised domain adaptation. In: NeurIPS, pp. 20612–20623 (2020)
Luo, Y., Liu, P., Zheng, L., Guan, T., Yu, J., Yang, Y.: Category-level adversarial adaptation for semantic segmentation using purified features. Trans. Pattern Anal. Mach. Intell. 44, 3940– 3956 (2021)
Luo, Y., Zheng, L., Guan, T., Yu, J., Yang, Y.: Taking a closer look at domain shift: category-level adversaries for semantics consistent domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2507–2516 (2019)
Luo, Y., Zheng, Z., Zheng, L., Guan, T., Yu, J., Yang, Y.: Macro-micro adversarial network for human parsing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 424–440. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_26
Maaten, L.v.d., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(November), 2579–2605 (2008)
Matsuura, T., Harada, T.: Domain generalization using a mixture of multiple latent domains. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11749–11756 (2020)
Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via IBN-Net. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 484–500. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_29
Paszke, A., et al.: Automatic differentiation in PyTorch. In: Neurips-W (2017)
Pei, Z., Cao, Z., Long, M., Wang, J.: Multi-adversarial domain adaptation. In: Thirty Second AAAI Conference on Artificial Intelligence (2018)
Peng, X., Huang, Z., Sun, X., Saenko, K.: Domain agnostic learning with disentangled representations. In: ICML, pp. 5102–5112 (2019)
Qiao, F., Peng, X.: Uncertainty-guided model generalization to unseen domains. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6790–6800 (2021)
Qiao, F., Zhao, L., Peng, X.: Learning to learn single domain generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12556–12565 (2020)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (May 2015)
Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7–12 June 2015. pp. 1–9. IEEE Computer Society (2015)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167–7176 (2017)
Wang, J., Lan, C., Liu, C., Ouyang, Y., Zeng, W., Qin, T.: Generalizing to unseen domains: a survey on domain generalization. arXiv preprint arXiv:2103.03097 (2021)
Wang, J., Jiang, J.: Learning across tasks for zero-shot domain adaptation from a single source domain. Trans. Pattern Anal. Mach. Intell. 44, 6264– 6279 (2021)
Wang, T., Zhou, C., Sun, Q., Zhang, H.: Causal attention for unbiased visual recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3091–3100 (2021)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. International Conference on Learning Representations (2018). https://openreview.net/forum?id=r1Ddp1-Rb
Zhang, Q., Zhang, J., Liu, W., Tao, D.: Category anchor-guided unsupervised domain adaptation for semantic segmentation. In: NeurIPS (2019)
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., Zhou, L., Xu, R., Cui, P., Shen, Z., Liu, H.: Domain-irrelevant representation learning for unsupervised domain generalization. arXiv preprint arXiv:2107.06219 (2021)
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)
Zhao, Y., et al.:Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6277–6286 (2021)
Zhou, K., Liu, Z., Qiao, Y., Xiang, T., Change Loy, C.: Domain generalization: A survey. arXiv preprint arXiv:2103.02503 (2021)
Zhu, B., Niu, Y., Hua, X.S., Zhang, H.: Cross-domain empirical risk minimization for unbiased long-tailed classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 3589–3597 (2022)
Acknowledgements
This work was supported by the National Key Research & Development Project of China (2021ZD0110700), the National Natural Science Foundation of China (U19B2043, 61976185), Zhejiang Natural Science Foundation (LR19F020002), Zhejiang Innovation Foundation (2019R52002), and the Fundamental Research Funds for the Central Universities (226-2022-00051).
Author information
Authors and Affiliations
Corresponding author
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
Lu, Y., Luo, Y., Pan, A., Mao, Y., Xiao, J. (2023). Domain Generalization with Global Sample Mixup. 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_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-25075-0_35
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)