Visualizing Residual Networks

TL;DR

This paper investigates the purpose of residual skip connections in residual networks, revealing that they help layers refine features and confirming known CNN behaviors through visualization and empirical analysis.

Contribution

It provides a detailed visualization and analysis of residual networks, challenging and confirming existing understanding of CNN layer functions.

Findings

Residual connections help layers refine features.

Visualizations confirm known CNN behaviors.

Residual networks learn features as expected.

Abstract

Residual networks are the current state of the art on ImageNet. Similar work in the direction of utilizing shortcut connections has been done extremely recently with derivatives of residual networks and with highway networks. This work potentially challenges our understanding that CNNs learn layers of local features that are followed by increasingly global features. Through qualitative visualization and empirical analysis, we explore the purpose that residual skip connections serve. Our assessments show that the residual shortcut connections force layers to refine features, as expected. We also provide alternate visualizations that confirm that residual networks learn what is already intuitively known about CNNs in general.