Abstract
In various visual classification tasks, we enjoy significant performance improvement by deep convolutional neural networks (CNNs). To further boost performance, it is effective to regularize feature representation learning of CNNs such as by considering margin to improve feature distribution across classes. In this paper, we propose a regularization method based on random rotation of feature vectors. Random rotation is derived from cone representation to describe angular margin of a sample. While it induces geometric regularization to randomly rotate vectors by means of rotation matrices, we theoretically formulate the regularization in a statistical form which excludes costly geometric rotation as well as effectively imposes rotation-based regularization on classification in training CNNs. In the experiments on classification tasks, the method is thoroughly evaluated from various aspects, while producing favorable performance compared to the other regularization methods. Codes are available at https://github.com/tk1980/StatRot.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For odd d, we apply \((d-1)/2\) with \(\boldsymbol{V}\in \Re ^{d\times d-1}\).
- 2.
ResNet10 produces \(d=512\)-dimensional features for \(C=1000\) ImageNet classes.
References
Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv 1607, 06450 (2016)
Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: CVPR, pp. 6541–6549 (2017)
Blaser, R., Fryzlewicz, P.: Random rotation ensembles. J. Mach. Learn. Rese. 17(4), 1–26 (2016)
Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. In: NeurIPS (2019)
Chen, B., Deng, W., Du, J.: Noisy softmax: improving the generalization ability of DCNN via postponing the early softmax saturation. In: CVPR, pp. 4021–4030 (2017)
Cohen, T.S., Welling, M.: Group equivariant convolutional networks. In: ICML, pp. 2990–2999 (2016)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)
Deng, J., Guo, J., Niannan, X., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: CVPR, pp. 4690–4699 (2019)
DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv. 1708.04552 (2017)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: Computer Vision and Pattern Recognition Workshop, pp. 178–178 (2004)
Ghiasi, G., Lin, T.Y., Le, Q.V.: Dropblock: a regularization method for convolutional networks. In: NeurIPS, pp. 3917–3924 (2018)
Golub, G.H., Loan, C.F.V.: Matrix Computations, 3rd edn. Johns Hopkins Univ. Press, London (1996)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv:1703.07737 (2017)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132–7141 (2018)
Hu, K., Póczos, B.: Rotationout as a regularization method for neural network. arXiv:1911.07427 (2019)
Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646–661. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_39
iNatrualist: The inaturalist 2018 competition dataset. https://github.com/visipedia/inat_comp/tree/master/2018 (2018)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. J. Mach. Learn. Res. 37, 448–456 (2015)
Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J., Kalantidis, Y.: Decoupling representation and classifier for long-tailed recognition. In: ICLR (2020)
Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Workshop on 3D Representation and Recognition, pp. 554–561 (2013)
Krogh, A., Hertz, J.A.: A simple weight decay can improve generalization. In: NeurIPS, pp. 950–957 (1991)
Lenc, K., Vedaldi, A.: Understanding image representations by measuring their equivariance and equivalence. In: CVPR, pp. 991–999 (2015)
Li, X., Chen, S., Hu, X., Yang, J.: Understanding the disharmony between dropout and batch normalization by variance shift. In: CVPR, pp. 2682–2690 (2019)
Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: CVPR, pp. 212–220 (2017)
Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: ICML, pp. 507–516 (2016)
Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: CVPR, pp. 2537–2546 (2019)
Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: CVPR workshop (2019)
Maji, S., Rahtu, E., Kannala, J., Blaschko, M.B., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv:1306.5151 (2013)
Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Dollár, P.: Designing network design spaces. In: CVPR, pp. 10428–10436 (2020)
Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17–35. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48881-3_2
Salimans, T., Kingma, D.P.: Weight normalization: a simple reparameterization to accelerate training of deep neural networks. In: NeurIPS (2016)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout : a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: The missing ingredient for fast stylization. arXiv:1607.08022 (2016)
Wang, H., et al.: Cosface: large margin cosine loss for deep face recognition. In: CVPR, pp. 5265–5274 (2018)
Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., Perona, P.: Caltech-UCSD Birds 200. Tech. Rep. CNS-TR-2010-001, California Institute of Technology (2010)
Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_31
Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR, pp. 3485–3492 (2010)
Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: ICCV, pp. 6023–6032 (2019)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV, pp. 1116–1124 (2015)
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452–1464 (2018)
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
Kobayashi, T. (2022). Rotation Regularization Without Rotation. 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 13685. Springer, Cham. https://doi.org/10.1007/978-3-031-19806-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-19806-9_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19805-2
Online ISBN: 978-3-031-19806-9
eBook Packages: Computer ScienceComputer Science (R0)