计算机科学
频道(广播)
频域
联营
光学(聚焦)
编码(集合论)
代表(政治)
算法
源代码
理论计算机科学
人工智能
计算机视觉
电信
操作系统
法学
程序设计语言
集合(抽象数据类型)
物理
光学
政治
政治学
作者
Zequn Qin,Pengyi Zhang,Fei Wu,Xi Li
标识
DOI:10.1109/iccv48922.2021.00082
摘要
Attention mechanism, especially channel attention, has gained great success in the computer vision field. Many works focus on how to design efficient channel attention mechanisms while ignoring a fundamental problem, i.e., channel attention mechanism uses scalar to represent channel, which is difficult due to massive information loss. In this work, we start from a different view and regard the channel representation problem as a compression process using frequency analysis. Based on the frequency analysis, we mathematically prove that the conventional global average pooling is a special case of the feature decomposition in the frequency domain. With the proof, we naturally generalize the compression of the channel attention mechanism in the frequency domain and propose our method with multi-spectral channel attention, termed as FcaNet. FcaNet is simple but effective. We can change a few lines of code in the calculation to implement our method within existing channel attention methods. Moreover, the proposed method achieves state-of-the-art results compared with other channel attention methods on image classification, object detection, and instance segmentation tasks. Our method could consistently outperform the baseline SENet, with the same number of parameters and the same computational cost. Our code and models are publicly available at https://github.com/cfzd/FcaNet.
科研通智能强力驱动
Strongly Powered by AbleSci AI