SRM : A Style-based Recalibration Module for Convolutional Neural Networks

TL;DR

This paper introduces SRM, a style-based recalibration module that enhances CNN performance by adaptively leveraging style information in feature maps, improving representational capacity with minimal computational overhead.

Contribution

The paper proposes a novel SRM module that uses style pooling and integration to recalibrate CNN features, outperforming existing methods like SE in various vision tasks.

Findings

SRM improves CNN accuracy on image recognition tasks.

SRM enhances style-related task performance.

SRM has negligible computational overhead.

Abstract

Following the advance of style transfer with Convolutional Neural Networks (CNNs), the role of styles in CNNs has drawn growing attention from a broader perspective. In this paper, we aim to fully leverage the potential of styles to improve the performance of CNNs in general vision tasks. We propose a Style-based Recalibration Module (SRM), a simple yet effective architectural unit, which adaptively recalibrates intermediate feature maps by exploiting their styles. SRM first extracts the style information from each channel of the feature maps by style pooling, then estimates per-channel recalibration weight via channel-independent style integration. By incorporating the relative importance of individual styles into feature maps, SRM effectively enhances the representational ability of a CNN. The proposed module is directly fed into existing CNN architectures with negligible overhead. We conduct comprehensive experiments on general image recognition as well as tasks related to styles, which verify the benefit of SRM over recent approaches such as Squeeze-and-Excitation (SE). To explain the inherent difference between SRM and SE, we provide an in-depth comparison of their representational properties.