Abstract
Convolutional Neural Networks (CNN) offer state of the art performance in various computer vision tasks. Many of those tasks require different subtypes of affine invariances (scale, rotational, translational) to image transformations. Convolutional layers are translation equivariant by design, but in their basic form lack invariances. In this work we investigate how best to include rotational invariance in a CNN for image classification. Our experiments show that networks trained with data augmentation alone can classify rotated images nearly as well as in the normal unrotated case; this increase in representational power comes only at the cost of training time. We also compare data augmentation versus two modified CNN models for achieving rotational invariance or equivariance, Spatial Transformer Networks and Group Equivariant CNNs, finding no significant accuracy increase with these specialized methods. In the case of data augmented networks, we also analyze which layers help the network to encode the rotational invariance, which is important for understanding its limitations and how to best retrain a network with data augmentation to achieve invariance to rotation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cohen, T., Welling, M.: Group equivariant convolutional networks. In: International Conference on Machine Learning, pp. 2990–2999 (2016)
Cohen, T.S., Welling, M.: Steerable CNNs. In: International Conference on Learning Representations (ICLR) (2017)
Cohen, T.S., Geiger, M., Köhler, J., Welling, M.: Spherical CNNs. In: Proceedings of the 6th International Conference on Learning Representations (ICLR) (2018)
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: Proceedings of the 2018 International Conference on Computer Vision (2017)
Dieleman, S., De Fauw, J., Kavukcuoglu, K.: Exploiting cyclic symmetry in convolutional neural networks. In: ICML 2016 Proceedings of the 33rd International Conference on International Conference on Machine Learning, vol. 48, pp. 1889–1898 (2016)
Dieleman, S., Willett, K.W., Dambre, J.: Rotation invariant convolutional neural networks for galaxy morphology prediction. Mon. Not. R. Astron. Soc. 450(2), 1441–1459. arXiv:1503.07077 (2015)
Gens, R., Domingos, P.M.: Deep symmetry networks. Adv. Neural. Inf. Process. Syst. 27, 2537–2545 (2014)
Jaderberg, M., Simonyan, K., Zisserman, A.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (NIPS 2015), pp. 2017–2025 (2015)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, University of Toronto, vol. 1, no. 4, p. 7 (2009)
Laptev, D., Savinov, N., Buhmann, J. M., Pollefeys, M.: TI-POOLING: transformation-invariant pooling for feature learning in convolutional neural networks. In: International Conference on Computer Vision and Pattern Recognition (CVPR) 2016, pp. 289–297. IEEE (2016)
Larochelle, H., Erhan, D., Courville, A., Bergstra, J., Bengio, Y.: An empirical evaluation of deep architectures on problems with many factors of variation. In: Proceedings of the 24th International Conference on Machine Learning, ICML 2007, pp. 473–480. ACM, New York (2007)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lenc, K., Vedaldi, A.: Understanding image representations by measuring their equivariance and equivalence. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 991–999, June 2015
Marcos, D., Volpi, M., Tuia, D.: Learning rotation invariant convolutional filters for texture classification. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2012–2017. IEEE, December 2016
Quiroga, F., Antonio, R., Ronchetti, F., Lanzarini, L.C., Rosete, A.: A study of convolutional architectures for handshape recognition applied to sign language. In XXIII Congreso Argentino de Ciencias de la Computación, La Plata (2017)
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Advances in Neural Information Processing Systems, pp. 3856–3866 (2017)
Weiler, M., Hamprecth, F., Storath, M.: Learning steerable filters for rotation equivariant CNNs. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Wu, F., Hu, P., Kong, D.: Flip-rotate-pooling convolution and split dropout on convolution neural networks for image classification. arXiv preprint arXiv:1507.08754 (2015)
Zhou, Y., Ye, Q., Qiu, Q., Jiao, J.: Oriented response networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4961–4970. IEEE, July 2017
Acknowledgements
The authors thank NVIDIA for their donation of a state of the art GPU which facilitated the execution of the experiments in this article.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Quiroga, F., Ronchetti, F., Lanzarini, L., Bariviera, A.F. (2020). Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks. In: Ferrer-Comalat, J., Linares-Mustarós, S., Merigó, J., Kacprzyk, J. (eds) Modelling and Simulation in Management Sciences. MS-18 2018. Advances in Intelligent Systems and Computing, vol 894. Springer, Cham. https://doi.org/10.1007/978-3-030-15413-4_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-15413-4_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-15412-7
Online ISBN: 978-3-030-15413-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)