Abstract
Self-supervised learning methods (SSL) have achieved significant success via maximizing the mutual information between two augmented views, where cropping is a popular augmentation technique. Cropped regions are widely used to construct positive pairs, while the remained regions after cropping have rarely been explored in existing methods, although they together constitute the same image instance and both contribute to the description of the category. In this paper, we make the first attempt to demonstrate the importance of both regions in cropping from a complete perspective and the effectiveness of using both regions via designing a simple yet effective pretext task called Region Contrastive Learning (RegionCL). Technically, to construct the two kinds of regions, we randomly crop a region (called the paste view) from each input image with the same size and swap them between different images to compose new images together with the remained regions (called the canvas view). Then, instead of taking the new images as a whole for positive or negative samples, contrastive pairs are efficiently constructed from the regional perspective based on the following simple criteria, i.e., each view is (1) positive with views augmented from the same original image and (2) negative with views augmented from other images. With minor modifications to popular SSL methods, RegionCL exploits those abundant pairs and helps the model distinguish the regions features from both canvas and paste views, therefore learning better visual representations. Experiments on ImageNet, MS COCO, and Cityscapes demonstrate that RegionCL improves MoCov2, DenseCL, and SimSiam by large margins and achieves state-of-the-art performance on classification, detection, and segmentation tasks. The code is publicly available at https://github.com/Annbless/RegionCL.
Y. Xu and Q. Zhang—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. In: International Conference on Learning Representations (2021)
Beyer, L., Hénaff, O.J., Kolesnikov, A., Zhai, X., van den Oord, A.: Are we done with ImageNet? arXiv preprint arXiv:2006.07159 (2020)
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882 (2020)
Caron, M., et al.: Emerging properties in self-supervised vision transformers. arXiv preprint arXiv:2104.14294 (2021)
Chen, K., Hong, L., Xu, H., Li, Z., Yeung, D.Y.: MultiSiam: self-supervised multi-instance siamese representation learning for autonomous driving. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7546–7554 (2021)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2017)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, vol. 1, pp. 1597–1607. PMLR (2020)
Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 22243–22255 (2020)
Chen, X., Fan, H., Girshick, R.B., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)
Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)
Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15750–15758 (2021)
Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9640–9649 (2021)
Contributors, M.: MMSegmentation: openmmlab semantic segmentation toolbox and benchmark (2020). https://github.com/open-mmlab/mmsegmentation
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248–255. IEEE (2009)
Ding, J., et al.: Unsupervised pretraining for object detection by patch reidentification. arXiv preprint arXiv:2103.04814 (2021)
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)
Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)
Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. arXiv preprint arXiv:2006.07733 (2020)
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 1735–1742. IEEE (2006)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9729–9738 (2020)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 2961–2969 (2017)
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 (CVPR), pp. 770–778 (2016)
Henaff, O.: Data-efficient image recognition with contrastive predictive coding. In: International Conference on Machine Learning, pp. 4182–4192. PMLR (2020)
Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 577–593. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_35
Li, C., Li, X., Zhang, L., Peng, B., Zhou, M., Gao, J.: Self-supervised pre-training with hard examples improves visual representations. arXiv preprint arXiv:2012.13493 (2020)
Li, J., Zhou, P., Xiong, C., Hoi, S.: Prototypical contrastive learning of unsupervised representations. In: International Conference on Learning Representations (2020)
Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. arXiv preprint arXiv:2203.16527 (2022)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 2980–2988 (2017)
Liu, S., Li, Z., Sun, J.: Self-EMD: self-supervised object detection without ImageNet. arXiv preprint arXiv:2011.13677 (2020)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022 (2021)
Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6707–6717 (2020)
Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving Jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69–84. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_5
van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2536–2544 (2016)
Pinheiro, P.O., Almahairi, A., Benmalek, R.Y., Golemo, F., Courville, A.: Unsupervised learning of dense visual representations. arXiv preprint arXiv:2011.05499 (2020)
Roh, B., Shin, W., Kim, I., Kim, S.: Spatially consistent representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1144–1153 (2021)
Shen, Z., Liu, Z., Liu, Z., Savvides, M., Darrell, T., Xing, E.: Un-mix: rethinking image mixtures for unsupervised visual representation learning. arXiv preprint arXiv:2003.05438 (2020)
Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: International Conference on Machine Learning, pp. 1139–1147. PMLR (2013)
Tao, C., et al.: Exploring the equivalence of siamese self-supervised learning via a unified gradient framework. arXiv preprint arXiv:2112.05141 (2021)
Tejankar, A., Koohpayegani, S.A., Pillai, V., Favaro, P., Pirsiavash, H.: ISD: self-supervised learning by iterative similarity distillation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9609–9618 (2021)
Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776–794. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_45
Tian, Y.: Deep contrastive learning is provably (almost) principal component analysis. arXiv preprint arXiv:2201.12680 (2022)
Wang, C., Xu, C., Tao, D.: Self-supervised pose adaptation for cross-domain image animation. IEEE Trans. Artif. Intell. 1(1), 34–46 (2020)
Wang, F., Liu, H.: Understanding the behaviour of contrastive loss. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2495–2504 (2021)
Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: International Conference on Machine Learning, pp. 9929–9939. PMLR (2020)
Wang, X., Zhang, R., Shen, C., Kong, T., Li, L.: Dense contrastive learning for self-supervised visual pre-training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3024–3033 (2021)
Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3733–3742 (2018)
Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432–448. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_26
Xie, E., et al.: DetCo: unsupervised contrastive learning for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 8392–8401 (2021)
Xie, Z., et al.: Self-supervised learning with swin transformers. arXiv preprint arXiv:2105.04553 (2021)
Xie, Z., Lin, Y., Zhang, Z., Cao, Y., Lin, S., Hu, H.: Propagate yourself: Exploring pixel-level consistency for unsupervised visual representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16684–16693 (2021)
Xu, Y., Zhang, J., Maybank, S.J., Tao, D.: DUT: learning video stabilization by simply watching unstable videos. IEEE Trans. Image Process. 31, 4306–4320 (2022)
Xu, Y., Zhang, J., Zhang, Q., Tao, D.: Vitpose: simple vision transformer baselines for human pose estimation. arXiv preprint arXiv:2204.12484 (2022)
Xu, Y., Zhang, Q., Zhang, J., Tao, D.: Vitae: vision transformer advanced by exploring intrinsic inductive bias. In: Advances in Neural Information Processing Systems, vol. 34, pp. 28522–28535 (2021)
Yang, C., Wu, Z., Zhou, B., Lin, S.: Instance localization for self-supervised detection pretraining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3987–3996 (2021)
Yang, J., Zhang, K., Cui, Z., Su, J., Luo, J., Wei, X.: InsCon: instance consistency feature representation via self-supervised learning. arXiv preprint arXiv:2203.07688 (2022)
You, Y., Gitman, I., Ginsburg, B.: Large batch training of convolutional networks. arXiv preprint arXiv:1708.03888 (2017)
Zhang, J., Tao, D.: Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things. IEEE Internet Things J. 8(10), 7789–7817 (2020)
Zhang, Q., Xu, Y., Zhang, J., Tao, D.: ViTAEV2: vision transformer advanced by exploring inductive bias for image recognition and beyond. arXiv preprint arXiv:2202.10108 (2022)
Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649–666. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_40
Zhao, Y., Wang, G., Luo, C., Zeng, W., Zha, Z.J.: Self-supervised visual representations learning by contrastive mask prediction. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10160–10169 (2021)
Acknowledgement
Mr. Yufei Xu, Mr. Qiming Zhang, and Dr. Jing Zhang are supported by ARC FL-170100117.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, Y., Zhang, Q., Zhang, J., Tao, D. (2022). RegionCL: Exploring Contrastive Region Pairs for Self-supervised Representation Learning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13693. Springer, Cham. https://doi.org/10.1007/978-3-031-19827-4_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-19827-4_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19826-7
Online ISBN: 978-3-031-19827-4
eBook Packages: Computer ScienceComputer Science (R0)