ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

Abstract

Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing methods dedicate to developing more sophisticated attention modules for achieving better performance, which inevitably increase model complexity. To overcome the paradox of performance and complexity trade-off, this paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain. By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity. Therefore, we propose a local cross-channel interaction strategy without dimensionality reduction, which can be efficiently implemented via $1D$ convolution. Furthermore, we develop a method to adaptively select kernel size of $1D$ convolution, determining coverage of local cross-channel interaction. The proposed ECA module is efficient yet effective, e.g., the parameters and computations of our modules against backbone of ResNet50 are 80 vs. 24.37M and 4.7e-4 GFLOPs vs. 3.86 GFLOPs, respectively, and the performance boost is more than 2% in terms of Top-1 accuracy. We extensively evaluate our ECA module on image classification, object detection and instance segmentation with backbones of ResNets and MobileNetV2. The experimental results show our module is more efficient while performing favorably against its counterparts.

Accepted to CVPR 2020; Project Page: https://github.com/BangguWu/ECANet

References in corpus (5)

• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
• Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
• ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions

Cited by in corpus (5)

• Hybrid Multiple Attention Network for Semantic Segmentation in Aerial Images
• FPB: Feature Pyramid Branch for Person Re-Identification
• Salient Positions based Attention Network for Image Classification
• Lossless Attention in Convolutional Networks for Facial Expression Recognition in the Wild
• Imponderous Net for Facial Expression Recognition in the Wild