失败
计算机科学
卷积神经网络
频道(广播)
核(代数)
卷积(计算机科学)
人工智能
维数之咒
计算
计算复杂性理论
还原(数学)
模式识别(心理学)
机器学习
计算机工程
人工神经网络
算法
并行计算
电信
数学
几何学
组合数学
作者
Qilong Wang,Banggu Wu,Pengfei Zhu,Peihua Li,Wangmeng Zuo,Qinghua Hu
出处
期刊:Cornell University - arXiv
日期:2019-01-01
被引量:17
标识
DOI:10.48550/arxiv.1910.03151
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI