Abstract
Mixup is an efficient data augmentation method which generates additional samples through respective convex combinations of original data points and labels. Although being theoretically dependent on data properties, Mixup is reported to perform well as a regularizer and calibrator contributing reliable robustness and generalization to neural network training. In this paper, inspired by Universum Learning which uses out-of-class samples to assist the target tasks, we investigate Mixup from a largely under-explored perspective - the potential to generate in-domain samples that belong to none of the target classes, that is, universum. We find that in the framework of supervised contrastive learning, universum-style Mixup produces surprisingly high-quality hard negatives, greatly relieving the need for a large batch size in contrastive learning. With these findings, we propose Universum-inspired Contrastive learning (UniCon), which incorporates Mixup strategy to generate universum data as g-negatives and pushes them apart from anchor samples of the target classes. Our approach not only improves Mixup with hard labels, but also innovates a novel measure to generate universum data. With a linear classifier on the learned representations, on Resnet-50, our method achieves 81.68% top-1 accuracy on CIFAR-100, surpassing the state of art by a significant margin of 5% with a much smaller batch size.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912–9924 (2020)
Carratino, L., Cissé, M., Jenatton, R., Vert, J.P.: On mixup regularization. arXiv preprint arXiv:2006.06049 (2020)
Chapelle, O., Agarwal, A., Sinz, F., Schölkopf, B.: An analysis of inference with the universum. In: Advances in Neural Information Processing Systems, vol. 20 (2007)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607. PMLR (2020)
Chen, X., Chen, S., Xue, H.: Universum linear discriminant analysis. Electron. Lett. 48(22), 1407–1409 (2012)
Cherkassky, V., Dhar, S., Dai, W.: Practical conditions for effectiveness of the universum learning. IEEE Trans. Neural Netw. 22(8), 1241–1255 (2011)
Chidambaram, M., Wang, X., Hu, Y., Wu, C., Ge, R.: Towards understanding the data dependency of mixup-style training. arXiv preprint arXiv:2110.07647 (2021)
Chou, H.-P., Chang, S.-C., Pan, J.-Y., Wei, W., Juan, D.-C.: Remix: rebalanced Mixup. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12540, pp. 95–110. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-65414-6_9
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: Learning augmentation strategies from data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 113–123 (2019)
Davoudian, A., Chen, L., Tu, H., Liu, M.: A workload-adaptive streaming partitioner for distributed graph stores. Data Sci. Eng. 6(2), 163–179 (2021)
Erichson, N.B., Lim, S.H., Utrera, F., Xu, W., Cao, Z., Mahoney, M.W.: Noisymix: Boosting robustness by combining data augmentations, stability training, and noise injections. arXiv preprint arXiv:2202.01263 (2022)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271–21284 (2020)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729–9738 (2020)
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.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Hou, J., Xu, J., Feng, R., Zhang, Y., Shan, F., Shi, W.: Cmc-cov19d: Contrastive mixup classification for covid-19 diagnosis. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 454–461 (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)
Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 21798–21809 (2020)
Khosla, P., et al.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661–18673 (2020)
Kim, S., Lee, G., Bae, S., Yun, S.Y.: Mixco: Mix-up contrastive learning for visual representation. arXiv preprint arXiv:2010.06300 (2020)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Lamb, A., Verma, V., Kannala, J., Bengio, Y.: Interpolated adversarial training: Achieving robust neural networks without sacrificing too much accuracy. In: Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, pp. 95–103 (2019)
Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N 7(7), 3 (2015)
Van den Oord, A., Li, Y., Vinyals, O., et al.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.037482(3), 4 (2018)
Qi, Z., Tian, Y., Shi, Y.: Twin support vector machine with universum data. Neural Netw. 36, 112–119 (2012)
Shafahi, A., et al.: Adversarial training for free! In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Shen, Y., Shen, Z., Wang, M., Qin, J., Torr, P., Shao, L.: You never cluster alone. In: Advances in Neural Information Processing Systems, vol. 34 (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)
Thulasidasan, S., Chennupati, G., Bilmes, J.A., Bhattacharya, T., Michalak, S.: On mixup training: Improved calibration and predictive uncertainty for deep neural networks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Weston, J., Collobert, R., Sinz, F., Bottou, L., Vapnik, V.: Inference with the universum. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 1009–1016 (2006)
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)
Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: Self-supervised learning via redundancy reduction. In: International Conference on Machine Learning, pp. 12310–12320. PMLR (2021)
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? arXiv preprint arXiv:2010.04819 (2020)
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
Han, A., Chen, S. (2023). Universum-Inspired Supervised Contrastive Learning. In: Li, B., Yue, L., Tao, C., Han, X., Calvanese, D., Amagasa, T. (eds) Web and Big Data. APWeb-WAIM 2022. Lecture Notes in Computer Science, vol 13422. Springer, Cham. https://doi.org/10.1007/978-3-031-25198-6_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-25198-6_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25197-9
Online ISBN: 978-3-031-25198-6
eBook Packages: Computer ScienceComputer Science (R0)