pith. sign in

arxiv: 1901.10208 · v1 · pith:CWE6KETVnew · submitted 2019-01-29 · 💻 cs.CV · cs.LG

A Push-Pull Layer Improves Robustness of Convolutional Neural Networks

classification 💻 cs.CV cs.LG
keywords layerpush-pullimagesconvolutionalnetworksnoiserobustnessclassification
0
0 comments X
read the original abstract

We propose a new layer in Convolutional Neural Networks (CNNs) to increase their robustness to several types of noise perturbations of the input images. We call this a push-pull layer and compute its response as the combination of two half-wave rectified convolutions, with kernels of opposite polarity. It is based on a biologically-motivated non-linear model of certain neurons in the visual system that exhibit a response suppression phenomenon, known as push-pull inhibition. We validate our method by substituting the first convolutional layer of the LeNet-5 and WideResNet architectures with our push-pull layer. We train the networks on nonperturbed training images from the MNIST, CIFAR-10 and CIFAR-100 data sets, and test on images perturbed by noise that is unseen by the training process. We demonstrate that our push-pull layers contribute to a considerable improvement in robustness of classification of images perturbed by noise, while maintaining state-of-the-art performance on the original image classification task.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Place recognition in gardens by learning visual representations: data set and benchmark analysis

    cs.CV 2019-06 unverdicted novelty 5.0

    An extended garden image dataset with pairwise ground truth is released and used to benchmark CNN place recognition models trained with contrastive loss, showing domain-specific improvement but limited generalization.