Open Access
Subscription Access
Open Access
Subscription Access
Robustcaps: A Transformation-Robust Capsule Network For Image Classification
Subscribe/Renew Journal
Geometric transformations of the training data as well as the test data present challenges to the use of deep neural networks to vision-based learning tasks. To address this issue, we present a deep neural network model that exhibits the desirable property of transformationrobustness. Our model, termed RobustCaps, uses group-equivariant convolutions in an improved capsule network model. RobustCaps uses a global context-normalised procedure in its routing algorithm to learn transformation-invariant part-whole relationships within image data. This learning of such relationships allows our model to outperform both capsule and convolutional neural network baselines on transformation-robust classification tasks. Specifically, RobustCaps achieves state-of-the-art accuracies on CIFAR-10, FashionMNIST, and CIFAR-100 when the images in these datasets are subjected to train and test-time rotations and translations.
Keywords
Deep Learning, Capsule Networks, Transformation Robustness, Equivariance.
Subscription
Login to verify subscription
User
Font Size
Information
- T. Cohen and M. Welling, “Group Equivariant Convolutional Networks”, Proceedings of International Conference on Machine Learning, pp. 2990-2999, 2016.
- M. Weiler and G. Cesa, “General E (2)-Equivariant Steerable CNNs”, Advances in Neural Information Processing Systems, Vol .32, pp. 1-15, 2019.
- T.S. Cohen and M. Welling, “Spherical CNNs”, Proceedings of International Conference on Learning Representations, pp. 1-7, 2018.
- G.E. Hinton, A. Krizhevsky and S.D. Wang, “Transforming Auto-Encoders”, Proceedings of International Conference on Artificial Neural Networks, pp. 44-51, 2011.
- S. Sabour and G.E. Hinton, “Dynamic Routing between Capsules”, Advances in Neural Information Processing Systems, Vol. 30, pp. 1-12, 2017.
- G.E. Hinton, S. Sabour and N. Frosst, “Matrix Capsules with EM Routing”, Proceedings of International Conference on Learning Representations, pp. 241-254, 2018.
- S.R. Venkataraman, S. Balasubramanian and R.R. Sarma, “Building Deep Equivariant Capsule Networks”, Proceedings of International Conference on Learning Representations, pp. 1-10, 2020.
- R. Pucci, C. Micheloni and N. Martinel, “Self-Attention Agreement Among Capsules”, Proceedings of International Conference on Computer Vision, pp. 272-280, 2021.
- J.E. Lenssen and P. Libuschewski, “Group Equivariant Capsule Networks”, Advances in Neural Information Processing Systems, Vol. 31, pp. 1-15, 2018.
- T.S. Cohen and M. Weiler, “A General Theory of Equivariant CNNs on Homogeneous Spaces”, Advances in Neural Information Processing Systems, Vol. 32, pp. 1-12, 2019.
- J. Rajasegaran, S. Seneviratne and R. Rodrigo, “Deepcaps: Going Deeper with Capsule Networks”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10725-10733, 2019.
- K. Ahmed and L. Torresani, “Star-Caps: Capsule Networks with Straight-Through Attentive Routing”, Advances in Neural Information Processing Systems, Vol. 32, pp. 167- 178, 2018.
- H. Xiao, K. Rasul and R. Vollgraf, “Fashion-Mnist: A Novel Image dataset for Benchmarking Machine Learning Algorithms”, Proceedings of International Conference on Computer Vision, pp. 1-8, 2017.
- A. Krizhevsky and G. Hinton, “Learning Multiple Layers of Features from Tiny Images”, Available at https://www.cs.toronto.edu/~kriz/learning-features-2009- TR.pdf, 2009.
- K. He and J. Sun, “Deep Residual Learning for Image Recognition”, Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
- D. Romero and M. Hoogendoorn, “Attentive Group Equivariant Convolutional Networks”, Proceedings of the IEEE International Conference on Machine Learning, pp. 8188-8199, 2020.
- I. Loshchilov and F. Hutter, “Decoupled Weight Decay Regularization”, Proceedings of International Conference on Learning Representations, Vol. 32, pp. 89-97, 2018.
- L.N. Smith and N. Topin, “Super-Convergence: Very Fast Training of Neural Networks using Large Learning Rates”, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, Vol. 11006, pp. 369-386, 2019.
Abstract Views: 160
PDF Views: 0