Lightweight Image Super-Resolution with Information Multi-distillation Network-优快云博客

本文链接：https://blog.youkuaiyun.com/zouxiaolv/article/details/125191379

本文介绍了论文中使用的Contrast-Aware Channel Attention Module (CCAM)，它通过计算特征图的方差和平均值，实现对通道级别的注意力机制。CCAM在IMDB模块中，通过特征融合和通道选择，提升模型性能。主要关注了特征图的统计计算和通道级特征调整技术。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

论文的contrast-aware channel attention module

import torch
import torch.nn as nn
#####完成的是一个特征图谱的平均值代码，对于H*W的特征图求取平均值
def mean_channels(F):
    assert(F.dim() == 4)
    spatial_sum = F.sum(3, keepdim=True).sum(2, keepdim=True)
    return spatial_sum / (F.size(2) * F.size(3))

###完成的是一个特征图谱求解方差代码

def stdv_channels(F):
    assert(F.dim() == 4)
    F_mean = mean_channels(F)
    F_variance = (F - F_mean).pow(2).sum(3, keepdim=True).sum(2, keepdim=True) / (F.size(2) * F.size(3))
    return F_variance.pow(0.5)

# contrast-aware channel attention module
class CCALayer(nn.Module):
    def __init__(self, channel, reduction=16):
        super(CCALayer, self).__init__()

        self.contrast = stdv_channels
        self.avg_pool = nn.AdaptiveAvgPool2d(1)#求得的是通道数不变，特征图谱的尺寸变成1
        self.conv_du = nn.Sequential(
            nn.Conv2d(channel, channel // reduction, 1, padding=0, bias=True),
            nn.ReLU(inplace=True),
            nn.Conv2d(channel // reduction, channel, 1, padding=0, bias=True),
            nn.Sigmoid()
        )


    def forward(self, x):
        y = self.contrast(x) + self.avg_pool(x)#这个是文章内的公式（5）
        y = self.conv_du(y)
        return x * y

对于IMDB的代码有一些讲解，channel split不是对半平分channel，而是采用：总的channel*ratia，剩余的channel=总的channel - 总的channel*ratia，

class IMDModule(nn.Module):
    def __init__(self, in_channels, distillation_rate=0.25):
        super(IMDModule, self).__init__()
        self.distilled_channels = int(in_channels * distillation_rate)
        self.remaining_channels = int(in_channels - self.distilled_channels)
        self.c1 = conv_layer(in_channels, in_channels, 3)
        self.c2 = conv_layer(self.remaining_channels, in_channels, 3)
        self.c3 = conv_layer(self.remaining_channels, in_channels, 3)
        self.c4 = conv_layer(self.remaining_channels, self.distilled_channels, 3)
        self.act = activation('lrelu', neg_slope=0.05)
        self.c5 = conv_layer(in_channels, in_channels, 1)
        self.cca = CCALayer(self.distilled_channels * 4)

    def forward(self, input):
        out_c1 = self.act(self.c1(input))
        distilled_c1, remaining_c1 = torch.split(out_c1, (self.distilled_channels, self.remaining_channels), dim=1)
        out_c2 = self.act(self.c2(remaining_c1))
        distilled_c2, remaining_c2 = torch.split(out_c2, (self.distilled_channels, self.remaining_channels), dim=1)
        out_c3 = self.act(self.c3(remaining_c2))
        distilled_c3, remaining_c3 = torch.split(out_c3, (self.distilled_channels, self.remaining_channels), dim=1)
        out_c4 = self.c4(remaining_c3)
        out = torch.cat([distilled_c1, distilled_c2, distilled_c3, out_c4], dim=1)
        out_fused = self.c5(self.cca(out)) + input
        return out_fused