Abstract
Domain generalization aims to enhance robustness of models to different domains, which is crucial for safety-critical systems in practice. In this paper, we propose a simple plug-in module to promote the ability of generalization for semantic segmentation networks without extra loss function. Firstly, we rethink the relationship between semantics and style in the sight of feature maps, and divide the channels of them into two kinds (i.e. style-sensitive channels and semantic-sensitive channels) via the variance of Gram matrix. Secondly, with the assumption that the domain shift mainly lies in style, a random erasure method is proposed to style-sensitive-channel features with the hope of learning domain invariant features and preventing model from over-fitting to specific domain. Extensive experiments demonstrate that the generalization of our proposed method outperforms existing approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Blanchard, G., Lee, G., Scott, C.: Generalizing from several related classification tasks to a new unlabeled sample. Adv. Neural Inf. Process. Syst. 24, 2178–2186 (2011)
Yue, X., Zhang. Y., Zhao, S., et al.: Domain randomization and pyramid consistency: simula-tion-to-real generalization without accessing target domain data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2100–2110 (2019)
Pan, X., Luo, P., Shi, J., et al.: Two at once: enhancing learning and generalization capacities via ibn-net. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 464–479 (2018)
Volpi, R., Murino, V.: Addressing model vulnerability to distributional shifts over image transformation sets. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7980–7989 (2019)
Li, Y., Tian, X., Gong, M., et al.: Deep domain generalization via conditional invariant adver-sarial networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 624–639 (2018)
Li, H., Pan, S.J., Wang, S., et al.: Domain generalization with adversarial feature learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5400–5409 (2018)
Choi, S., Jung, S., Yun, H., et al.: RobustNet: improving domain generalization in urban-scene segmentation via instance selective whitening. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11580–11590 (2021)
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)
Ioffe, S, Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456. PMLR (2015)
Ghifary, M., Kleijn, W.B., Zhang, M., et al.:Domain generalization for object recognition with multi-task autoencoders. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2551–2559 (2015)
Muande, K., Balduzzi, D., Schölkopf, B.: Domain generalization via invariant feature representation. In: International Conference on Machine Learning, pp. 10–18. PMLR (2013)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmenta-tion. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Patt. Anal. Mach. Intell. 39(12), 2481–2495 (2017)
Chen, L.C., Papandreou, G., Kokkinos, I., et al.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. IEEE Trans. Patt. Aanal. Mach. Intell. 40(4), 834–848 (2017)
He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)
Zhao, H., Shi, J., Qi, X., et al.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vsion and Pattern Recognition, pp. 2881–2890 (2017)
Chen, L.C., Papandreou, G., Schroff, F., et al.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)
Chen, L.C., Zhu, Y., Papandreou, G., et al.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801–818 (2018)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv pre-print arXiv:1511.07122 (2015)
Paszke, A., Gross, S., Massa, F., et al.: Pytorch: an imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)
Cordts, M., Omran, M., Ramos, S., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3223 (2016)
Yu, F., Chen, H., Wang, X., et al.: Bdd100k: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2636–2645 (2020)
Neuhold, G., Ollmann, T., Rota Bulo, S., et al.: The mapillary vistas dataset for semantic understanding of street scenes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4990–4999 (2017)
Ros, G., Sellart, L., Materzynska, J., et al.: The synthia dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3234–3243 (2016)
Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102–118. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_7
Liu, W., Rabinovich, A., Berg, A.C.: Parsenet: looking wider to see better. arXiv preprint arXiv:1506.04579 (2015)
Li, Y., Fang, C., Yang, J., et al.: Universal style transfer via feature transforms. arXiv preprint arXiv:1705.08086 (2017)
Acknowledgement
This work is partially supported by National Natural Science Foundation of China (Grants no. 61772568), Guangdong Basic and Applied Basic Research Foundation (Grant no. 2019A1515012029), and Youth science and technology innovation talent of Guangdong Special Support Program.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Su, S., Wang, H., Yang, M. (2021). Suppressing Style-Sensitive Features via Randomly Erasing for Domain Generalizable Semantic Segmentation. In: Ma, H., et al. Pattern Recognition and Computer Vision. PRCV 2021. Lecture Notes in Computer Science(), vol 13022. Springer, Cham. https://doi.org/10.1007/978-3-030-88013-2_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-88013-2_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88012-5
Online ISBN: 978-3-030-88013-2
eBook Packages: Computer ScienceComputer Science (R0)