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.
A Push-Pull Layer Improves Robustness of Convolutional Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
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.
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Place recognition in gardens by learning visual representations: data set and benchmark analysis
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.