CBAM：通道注意力+空间注意力-pytroch

https://blog.csdn.net/oYeZhou/article/details/116664508

论文地址：https://openaccess.thecvf.com/content_ECCV_2018/papers/Sanghyun_Woo_Convolutional_Block_Attention_ECCV_2018_paper.pdf

1、动机

卷积操作是通过混合通道和空间两个维度的信息来间特征提取的。在注意力方面，SE仅关注了通道注意力，没考虑空间方面的注意力。因此，本文提出了 CBAM——一种同时关注通道和空间注意力的卷积模块，可以用于CNNs架构中，以提升feature map的特征表达能力。

2、方法

CAM和SAM的架构如图2所示：

3、Pytorch实现

CBAM包含了个子模块：CAM和SAM，使用时，分别实例化它们，然后顺序应用在某个feature map之后即可。下面给出其Pytorch代码：

import torch
from torch import nn
 
 
class ChannelAttention(nn.Module):
    def __init__(self, in_planes, ratio=16):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)
 
        self.fc1   = nn.Conv2d(in_planes, in_planes // 16, 1, bias=False)
        self.relu1 = nn.ReLU()
        self.fc2   = nn.Conv2d(in_planes // 16, in_planes, 1, bias=False)
 
        self.sigmoid = nn.Sigmoid()
 
    def forward(self, x):
        avg_out = self.fc2(self.relu1(self.fc1(self.avg_pool(x))))
        max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
        out = avg_out + max_out
        return self.sigmoid(out)
 

class SpatialAttention(nn.Module):
    def __init__(self, kernel_size=7):
        super(SpatialAttention, self).__init__()
 
        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1
 
        self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
        self.sigmoid = nn.Sigmoid()
        self.register_buffer()
 
    def forward(self, x):
        avg_out = torch.mean(x, dim=1, keepdim=True)
        max_out, _ = torch.max(x, dim=1, keepdim=True)
        x = torch.cat([avg_out, max_out], dim=1)
        x = self.conv1(x)
        return self.sigmoid(x)