深入理解CV中的Attention机制之CBAM
CV中的Attention机制汇总(二):CBAM
CBAM:Convolutional Block Attention Module
论文链接:CBAM(ECCV 2018)
1. 摘要
1.1 CBAM概要
Given an intermediate feature map, our module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. 与SE模块不同,CBAM结合了使用了通道 与 空间注意力机制。作者认为通道注意力决定了“what is important",空间注意力
共有 0 条评论