Invariant Integration in Deep Convolutional Feature Space
This addresses the challenge of improving robustness and efficiency in vision-related classification tasks, particularly when data is scarce, though it is incremental as it builds on existing invariance methods.
The paper tackled the problem of incorporating prior knowledge into deep neural networks by enforcing feature space invariances using a novel invariant integration layer, achieving state-of-the-art performance on the Rotated-MNIST dataset, especially with limited data.
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.