SimAM: A Simple, Parameter-Free Attention Module for
Convolutional Neural Networks
Lingxiao Yang 1 2 3 Ru-Yuan Zhang 4 5 Lida Li 6 Xiaohua Xie 1 2 3
Abstract
ResNet-50
In this paper, we propose a conceptually simple
but very effective attention module for Convolu-
tional Neural Networks (ConvNets). In contrast to
existing channel-wise and spatial-wise attention
+ SE
m ...


雷达卡




京公网安备 11010802022788号







