Abstract
Mixup is one of data augmentation methods for image recognition task, which generate data by mixing two images. Mixup randomly samples two images from training data without considering the similarity of these data and classes. This random sampling generates mixed samples with low similarities, which makes a network training difficult and complicated. In this paper, we propose a mixup considering super-class. Super-class is a superordinate categorization of object classes. The proposed method tends to generate mixed samples with the almost same mixing ratio in the case of the same super-class. In contrast, given two images having different super-classes, we generate samples largely containing one image’s data. Consequently, a network can train the features between similar object classes. Furthermore, we apply the proposed method into a mutual learning framework, which would improve the network output used for mutual learning. The experimental results demonstrate that the proposed method improves the recognition accuracy on a single model training and mutual training. And, we analyze the attention maps of networks and show that the proposed method also improves the highlighted region and makes a network correctly focuses on the target object.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In [17], \(\alpha \in [0.1, 0.4]\) is used for their experiments. In this paper, we discuss the other values of \(\alpha \) and the effects of these values in our experiments.
References
Chen, P., Liu, S., Zhao, H., Jia, J.: Gridmask data augmentation. arXiv preprint arXiv:2001.04086 (2020)
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation strategies from data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2009)
Devries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)
Fukui, H., Hirakawa, T., Yamashita, T., Fujiyoshi, H.: Attention branch network: learning of attention mechanism for visual explanation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Furlanello, T., Lipton, Z., Tschannen, M., Itti, L., Anandkumar, A.: Born again neural networks. In: Proceedings of the International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 80, pp. 1607–1616 (2018)
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) (2016)
Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Proceedings of NIPS workshop on Deep Learning and Representation Learning (2014)
Kim, J.H., Choo, W., Song, H.O.: Puzzle mix: exploiting saliency and local statistics for optimal mixup. In: Proceedings of the International Conference on Machine Learning (ICML) (2020)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images, Technical report. University of Tront (2009)
Kumar Singh, K., Jae Lee, Y.: Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)
Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)
Mirzadeh, S.I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., Ghasemzadeh, H.: Improved knowledge distillation via teacher assistant. Proc. AAAI Conf. Artif. Intell. 34(04), 5191–5198 (2020)
Uddin, A.F.M.S., Monira, M.S., Shin, W., Chung, T., Bae, S.H.: SaliencyMix: a saliency guided data augmentation strategy for better regularization. In: International Conference on Learning Representations (2021)
Verma, V., et al.: Manifold mixup: better representations by interpolating hidden states. In: Proceedings of the International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 97, pp. 6438–6447 (2019)
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 International Conference on Computer Vision (ICCV) (2019)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)
Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Fujii, S., Okamoto, N., Seo, T., Hirakawa, T., Yamashita, T., Fujiyoshi, H. (2022). Super-Class Mixup for Adjusting Training Data. In: Wallraven, C., Liu, Q., Nagahara, H. (eds) Pattern Recognition. ACPR 2021. Lecture Notes in Computer Science, vol 13189. Springer, Cham. https://doi.org/10.1007/978-3-031-02444-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-02444-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02443-6
Online ISBN: 978-3-031-02444-3
eBook Packages: Computer ScienceComputer Science (R0)