Locality-Promoting Representation Learning

Abstract

This work investigates fundamental questions related to learning features in convolutional neural networks (CNN). Empirical findings across multiple architectures such as VGG, ResNet, Inception, DenseNet and MobileNet indicate that weights near the center of a filter are larger than weights on the outside. Current regularization schemes violate this principle. Thus, we introduce Locality-promoting Regularization (LOCO-Reg), which yields accuracy gains across multiple architectures and datasets. We also show theoretically that the empirical finding is a consequence of maximizing feature cohesion under the assumption of spatial locality.