Visual response inhibition for increased robustness of convolutional networks to distribution shifts

Convolutional neural networks have been shown to suffer from distribution shifts
in the test data, for instance caused by the so called common corruptions and
perturbations. Test images can contain noise, digital transformations, and blur
that were not present in the training data, negatively impacting the performance of
trained models. Humans experience much stronger robustness to noise and visual
distortions than deep networks. In this work, we explore the effectiveness of a
neuronal response inhibition mechanism, called push-pull, observed in the early
part of the visual system, to increase the robustness of deep convolutional networks.
We deploy a Push-Pull inhibition layer as a replacement of the initial convolutional
layers (input layer and in the first block of residual and dense architectures) of
standard convolutional networks for image classification. We show that the PushPull inhibition component increases the robustness of standard networks for image
classification to distribution shifts on the CIFAR10-C and CIFAR10-P test sets.