In this contribution, we show how to incorporate prior knowledge to a deep neural network architecture in a principled manner. We enforce feature space invariances using a novel layer based on invariant integration. This allows us to construct a complete feature space invariant to finite transformation groups. We apply our proposed layer to explicitly insert invariance properties for vision-related classification tasks, demonstrate our approach for the case of rotation invariance and report state-of-the-art performance on the Rotated-MNIST dataset. Our method is especially beneficial when training with limited data.
@article{arxiv.2004.09166,
title = {Invariant Integration in Deep Convolutional Feature Space},
author = {Matthias Rath and Alexandru Paul Condurache},
journal= {arXiv preprint arXiv:2004.09166},
year = {2020}
}
Comments
Accepted at ESANN 2020 (European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning)