SENet、CBAM区别和应用以及对应的pytorch代码

SENet和CBAM都是用于图像分类的注意力机制模块，可以提高模型的性能。

SENet（Squeeze-and-Excitation Networks）通过引入一个称为“Squeeze-and-Excitation block”的模块来增强卷积神经网络的表示能力。SE block包含两个步骤：第一步是全局平均池化，将每个通道的特征图转换为一个标量；第二步是使用两个全连接层来学习每个通道的权重，以增强有用信息并削减噪声。SENet的优化是通过提高通道相关性来实现的。

CBAM（Convolutional Block Attention Module）是另一种注意力机制模块，它通过在通道和空间维度上使用注意力来提高卷积神经网络的性能。CBAM模块包含两个分支：一个分支用于学习通道级别的注意力，另一个分支用于学习空间级别的注意力。通过这种方式，CBAM可以提高模型的表示能力并消除噪声。

以下是SENet和CBAM的Pytorch实现代码：

SENet:

import torch.nn as nn
import torch

class SEBlock(nn.Module):
    def __init__(self, channel, reduction=16):
        super(SEBlock, self).__init__()

        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
            nn.Linear(channel, channel // reduction, bias=False),
            nn.ReLU(inplace=True),
            nn.Linear(channel // reduction, channel, bias=False),
            nn.Sigmoid()
        )

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b, c, 1, 1)
        return x * y.expand_as(x)

CBAM:

import torch.nn as nn
import torch

class ChannelAttention(nn.Module):
    def __init__(self, channel, reduction=16):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)

        self.fc1   = nn.Conv2d(channel, channel // reduction, 1, bias=False)
        self.relu1 = nn.ReLU()
        self.fc2   = nn.Conv2d(channel // reduction, channel, 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()

    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)

class CBAM(nn.Module):
    def __init__(self, channel, reduction=16, kernel_size=7):
        super(CBAM, self).__init__()
        self.ChannelGate = ChannelAttention(channel, reduction=reduction)
        self.SpatialGate = SpatialAttention(kernel_size=kernel_size)

    def forward(self, x):
        x_out = self.ChannelGate(x) * x
        x_out = self.SpatialGate(x_out) * x_out
        return x_out