# Locality-Promoting Representation Learning

arXiv: https://arxiv.org/abs/1905.10661 · HTML: https://mlsanity.com/paper/1905.10661/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2019.

## Built on by (most cited first, 1 of 1)

- [Domain Transformer: Predicting Samples of Unseen, Future Domains](https://mlsanity.com/paper/2106.06057/) (2021)

## Abstract (arXiv)

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.