1.计算机视觉中的注意力机制
一般来说，注意力机制通常被分为以下基本四大类：
通道注意力 Channel Attention
空间注意力机制 Spatial Attention
时间注意力机制 Temporal Attention
分支注意力机制 Branch Attention
1.1.CBAM：通道注意力和空间注意力的集成者
轻量级的卷积注意力模块，它结合了通道和空间的注意力机制模块
论文题目：《CBAM: Convolutional Block Attention Module》 论文地址： https://arxiv.org/pdf/1807.06521.pdf
上图可以看到，CBAM包含CAM（Channel Attention Module）和SAM（Spartial Attention Module）两个子模块，分别进行通道和空间上的Attention。这样不只能够节约参数和计算力，并且保证了其能够做为即插即用的模块集成到现有的网络架构中去。
1.2 GAM：Global Attention Mechanism
超越CBAM，全新注意力GAM：不计成本提高精度！ 论文题目：Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions 论文地址：https://paperswithcode.com/paper/global-attention-mechanism-retain-information
从整体上可以看出，GAM和CBAM注意力机制还是比较相似的，同样是使用了通道注意力机制和空间注意力机制。但是不同的是对通道注意力和空间注意力的处理。
1.3 ResBlock_CBAM
CBAM结构其实就是将通道注意力信息核空间注意力信息在一个block结构中进行运用。
在resnet中实现cbam：即在原始block和残差结构连接前，依次通过channel attention和spatial attention即可。
1.4性能评价
2.Yolov5加入CBAM、GAM
2.1 CBAM加入common.py中
代码语言：javascript复制class ChannelAttentionModule(nn.Module):
def __init__(self, c1, reduction=16,light=False):
super(ChannelAttentionModule, self).__init__()
mid_channel = c1 // reduction
self.light=light
self.avg_pool = nn.AdaptiveAvgPool2d(1)
if self.light:
self.max_pool = nn.AdaptiveMaxPool2d(1)
self.shared_MLP = nn.Sequential(
nn.Linear(in_features=c1, out_features=mid_channel),
nn.LeakyReLU(0.1, inplace=True),
nn.Linear(in_features=mid_channel, out_features=c1)
)
else:
self.shared_MLP = nn.Conv2d(c1, c1, 1, 1, 0, bias=True)
self.act = nn.Sigmoid()
def forward(self, x):
if self.light:
avgout = self.shared_MLP(self.avg_pool(x).view(x.size(0),-1)).unsqueeze(2).unsqueeze(3)
maxout = self.shared_MLP(self.max_pool(x).view(x.size(0),-1)).unsqueeze(2).unsqueeze(3)
fc_out=(avgout maxout)
else:
fc_out=(self.shared_MLP(self.avg_pool(x)))
return x * self.act(fc_out)
class SpatialAttentionModule(nn.Module): ##update:coding-style FOR LIGHTING
def __init__(self, kernel_size=7):
super().__init__()
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
padding = 3 if kernel_size == 7 else 1
self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
self.act = nn.Sigmoid()
def forward(self, x):
return x * self.act(self.cv1(torch.cat([torch.mean(x, 1, keepdim=True), torch.max(x, 1, keepdim=True)[0]], 1)))
class CBAM(nn.Module):
def __init__(self, c1,c2,k=7):
super().__init__()
self.channel_attention = ChannelAttentionModule(c1)
self.spatial_attention = SpatialAttentionModule(k)
def forward(self, x):
return self.spatial_attention(self.channel_attention(x))2.2 GAM加入common.py中
代码语言：javascript复制def channel_shuffle(x, groups=2): ##shuffle channel
#RESHAPE----->transpose------->Flatten
B, C, H, W = x.size()
out = x.view(B, groups, C // groups, H, W).permute(0, 2, 1, 3, 4).contiguous()
out=out.view(B, C, H, W)
return out
class GAM_Attention(nn.Module):
#https://paperswithcode.com/paper/global-attention-mechanism-retain-information
def __init__(self, c1, c2, group=True,rate=4):
super(GAM_Attention, self).__init__()
self.channel_attention = nn.Sequential(
nn.Linear(c1, int(c1 / rate)),
nn.ReLU(inplace=True),
nn.Linear(int(c1 / rate), c1)
)
self.spatial_attention = nn.Sequential(
nn.Conv2d(c1, c1//rate, kernel_size=7, padding=3,groups=rate)if group else nn.Conv2d(c1, int(c1 / rate), kernel_size=7, padding=3),
nn.BatchNorm2d(int(c1 /rate)),
nn.ReLU(inplace=True),
nn.Conv2d(c1//rate, c2, kernel_size=7, padding=3,groups=rate) if group else nn.Conv2d(int(c1 / rate), c2, kernel_size=7, padding=3),
nn.BatchNorm2d(c2)
)
def forward(self, x):
b, c, h, w = x.shape
x_permute = x.permute(0, 2, 3, 1).view(b, -1, c)
x_att_permute = self.channel_attention(x_permute).view(b, h, w, c)
x_channel_att = x_att_permute.permute(0, 3, 1, 2)
# x_channel_att=channel_shuffle(x_channel_att,4) #last shuffle
x = x * x_channel_att
x_spatial_att = self.spatial_attention(x).sigmoid()
x_spatial_att=channel_shuffle(x_spatial_att,4) #last shuffle
out = x * x_spatial_att
#out=channel_shuffle(out,4) #last shuffle
return out 2.4 GAM加入common.py中加入common.py中
代码语言：javascript复制class ResBlock_CBAM(nn.Module):
def __init__(self, in_places, places, stride=1, downsampling=False, expansion=4):
super(ResBlock_CBAM, self).__init__()
self.expansion = expansion
self.downsampling = downsampling
self.bottleneck = nn.Sequential(
nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=1, stride=1, bias=False),
nn.BatchNorm2d(places),
nn.LeakyReLU(0.1, inplace=True),
nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False),
nn.BatchNorm2d(places),
nn.LeakyReLU(0.1, inplace=True),
nn.Conv2d(in_channels=places, out_channels=places * self.expansion, kernel_size=1, stride=1,
bias=False),
nn.BatchNorm2d(places * self.expansion),
)
self.cbam = CBAM(c1=places * self.expansion, c2=places * self.expansion, )
if self.downsampling:
self.downsample = nn.Sequential(
nn.Conv2d(in_channels=in_places, out_channels=places * self.expansion, kernel_size=1, stride=stride,
bias=False),
nn.BatchNorm2d(places * self.expansion)
)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
residual = x
out = self.bottleneck(x)
out = self.cbam(out)
if self.downsampling:
residual = self.downsample(x)
out = residual
out = self.relu(out)
return out2.3 CBAM、GAM加入yolo.py中
代码语言：javascript复制if m in {
Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, C2f,CBAM,ResBlock_CBAM,GAM_Attention}:详见：
by CSDN AI小怪兽 https://blog.csdn.net/m0_63774211/article/details/129611391
我正在参与2023腾讯技术创作特训营第三期有奖征文，组队打卡瓜分大奖！
