SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks

By Lingxiao Yang, Ru-Yuan Zhang, Lida Li, Xiaohua Xie. International Conference on Machine Learning, 2021

1,765 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/3a173a2042b3d18d21f59187f1e5d7d83e791635

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Man Yao
2. Yonghong Tian
3. Guangshe Zhao
4. Guoqi Li
5. Hengyu Zhang
6. Lei Deng
7. Yifan Hu
8. Bo Xu

Citations in the corpus

• Attention Spiking Neural Networks (2022, methodology): “Actually, gt(·) and gc(·) can be acted by various attention modules, including classic SE [19], energy-efficient ECA [46], and parameter-free SimAM [31], etc.”