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

03/26/2019
by   Hyunjae Lee, et al.
20

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.

READ FULL TEXT

page 6

page 8

page 9

page 10

research
10/29/2019

Style Mixer: Semantic-aware Multi-Style Transfer Network

Recent neural style transfer frameworks have obtained astonishing visual...
research
05/21/2018

Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks

Real-world image recognition is often challenged by the variability of v...
research
08/15/2016

Every Filter Extracts A Specific Texture In Convolutional Neural Networks

Many works have concentrated on visualizing and understanding the inner ...
research
08/10/2019

Channel Decomposition on Generative Networks

This work presents a method to decompose a layer of the generative netwo...
research
04/29/2021

Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps

"Lightweight convolutional neural networks" is an important research top...
research
03/10/2020

Channel Attention with Embedding Gaussian Process: A Probabilistic Methodology

Channel attention mechanisms, as the key components of some modern convo...
research
08/10/2019

Channel Decomposition into Painting Actions

This work presents a method to decompose a convolutional layer of the de...

Please sign up or login with your details

Forgot password? Click here to reset