Abstract
We consider a framework including multiple augmentation regularisation by generalised divergences to induce invariance for non-group transformations during training of convolutional neural networks. Experiments on supervised classification of images at different scales not considered during training illustrate that our proposed method performs better than classical data augmentation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Altstidl, T., et al.: Just a matter of scale? reevaluating scale equivariance in convolutional neural networks. arXiv preprint arXiv:2211.10288 (2022)
Andén, J., Mallat, S.: Deep scattering spectrum. IEEE Trans. Signal Process. 62(16), 4114–4128 (2014)
Barnard, E., Casasent, D.: Invariance and neural nets. IEEE Trans. Neural Netw. 2(5), 498–508 (1991)
Benton, G., Finzi, M., Izmailov, P., Wilson, A.G.: Learning invariances in neural networks from training data. Adv. Neural. Inf. Process. Syst. 33, 17605–17616 (2020)
Botev, A., Bauer, M., De, S.: Regularising for invariance to data augmentation improves supervised learning. arXiv preprint arXiv:2203.03304 (2022)
Bronstein, M.M., Bruna, J., Cohen, T., Veličković, P.: Geometric deep learning: Grids, groups, graphs, geodesics, and gauges. arXiv preprint arXiv:2104.13478 (2021)
Cazelles, E., Tobar, F., Fontbona, J.: A novel notion of barycenter for probability distributions based on optimal weak mass transport. Adv. Neural. Inf. Process. Syst. 34, 13575–13586 (2021)
Cesa, G., Lang, L., Weiler, M.: A program to build E(N)-equivariant steerable CNNs. In: International Conference on Learning Representations (2022)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
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, W., Tian, L., Fan, L., Wang, Y.: Augmentation invariant training. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pp. 0–0 (2019)
Cohen, T., Welling, M.: Group equivariant convolutional networks. In: International Conference on Machine Learning, pp. 2990–2999. PMLR (2016)
Fort, S., Brock, A., Pascanu, R., De, S., Smith, S.L.: Drawing multiple augmentation samples per image during training efficiently decreases test error. arXiv preprint arXiv:2105.13343 (2021)
Fralick, S.: Learning to recognize patterns without a teacher. IEEE Trans. Inf. Theory 13(1), 57–64 (1967)
Geiping, J., Goldblum, M., Somepalli, G., Shwartz-Ziv, R., Goldstein, T., Wilson, A.G.: How much data are augmentations worth? an investigation into scaling laws, invariance, and implicit regularization. arXiv preprint arXiv:2210.06441 (2022)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Haasdonk, B., Vossen, A., Burkhardt, H.: Invariance in kernel methods by Haar-Integration kernels. In: Kalviainen, H., Parkkinen, J., Kaarna, A. (eds.) SCIA 2005. LNCS, vol. 3540, pp. 841–851. Springer, Heidelberg (2005). https://doi.org/10.1007/11499145_85
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)
Kokkinos, I.: Pushing the boundaries of boundary detection using deep learning. arXiv preprint arXiv:1511.07386 (2015)
Kondor, R., Trivedi, S.: On the generalization of equivariance and convolution in neural networks to the action of compact groups. In: International Conference on Machine Learning, pp. 2747–2755. PMLR (2018)
Kullback, S.: Information theory and statistics. Courier Corporation (1997)
Laptev, D., Savinov, N., Buhmann, J.M., Pollefeys, M.: Ti-pooling: transformation-invariant pooling for feature learning in convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 289–297 (2016)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Mroueh, Y., Voinea, S., Poggio, T.A.: Learning with group invariant features: A kernel perspective. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Penaud-Polge, V., Velasco-Forero, S., Angulo, J.: Fully trainable Gaussian derivative convolutional layer. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 2421–2425. IEEE (2022)
Penaud-Polge, V., Velasco-Forero, S., Angulo, J.: Genharris-resnet: A rotation invariant neural network based on elementary symmetric polynomials. In: Scale Space and Variational Methods in Computer Vision, pp. 149–161. Springer International Publishing, Cham (2023). https://doi.org/10.1007/978-3-031-31975-4_12
Procesi, C.: Lie groups: an approach through invariants and representations, vol. 115. Springer (2007). https://doi.org/10.1007/978-0-387-28929-8
Rota, G.C.: Reynolds operators. In: Proceedings of Symposia in Applied Mathematics. vol. 16, pp. 70–83. American Mathematical Society Providence, RI (1964)
Sangalli, M., Blusseau, S., Velasco-Forero, S., Angulo, J.: Scale equivariant neural networks with morphological scale-spaces. In: Lindblad, J., Malmberg, F., Sladoje, N. (eds.) DGMM 2021. LNCS, vol. 12708, pp. 483–495. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-76657-3_35
Sangalli, M., Blusseau, S., Velasco-Forero, S., Angulo, J.: Moving frame net: SE (3)-equivariant network for volumes. In: NeurIPS Workshop on Symmetry and Geometry in Neural Representations, pp. 81–97. PMLR (2023)
Scudder, H.: Adaptive communication receivers. IEEE Trans. Inf. Theory 11(2), 167–174 (1965)
Sgarro, A.: Informational divergence and the dissimilarity of probability distributions. Calcolo 18(3), 293–302 (1981)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. big data 6(1), 1–48 (2019)
Sibson, R.: Information radius. Zeitschrift für Wahrscheinlichkeitstheorie und verwandte Gebiete 14(2), 149–160 (1969)
Smets, B.M., Portegies, J., Bekkers, E.J., Duits, R.: Pde-based group equivariant convolutional neural networks. J. Math. Imag. Vision 65(1), 209–239 (2023)
Wilk, M.v.d., Bauer, M., John, S., Hensman, J.: Learning invariances using the marginal likelihood. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 9960–9970 (2018)
Worrall, D., Welling, M.: Deep scale-spaces: Equivariance over scale. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Yang, S., Dong, Y., Ward, R., Dhillon, I.S., Sanghavi, S., Lei, Q.: Sample efficiency of data augmentation consistency regularization. In: AISTATS (2023)
Zhang, H., Cissé, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. In: ICLR (2018)
Zhu, X., Ghahramani, Z., Lafferty, J.D.: Semi-supervised learning using Gaussian fields and harmonic functions. In: Proceedings of the 20th International conference on Machine learning (ICML-03), pp. 912–919 (2003)
Acknowledgements
This work was granted access to the Jean Zay supercomputer under the allocation 2022-AD011012212R2.
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
Velasco-Forero, S. (2023). Can Generalised Divergences Help for Invariant Neural Networks?. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2023. Lecture Notes in Computer Science, vol 14071. Springer, Cham. https://doi.org/10.1007/978-3-031-38271-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-38271-0_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-38270-3
Online ISBN: 978-3-031-38271-0
eBook Packages: Computer ScienceComputer Science (R0)