Year: 2020
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Rath, Matthias, Condurache, Alexandru Paul
Institution: Robert Bosch (Germany)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3017014306