Invariant Integration in Deep Convolutional Feature Space

04/20/2020
by   Matthias Rath, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset