这是一篇arXiv上的文章，也是关于注意力机制的工作，不过是在图像分割使用通道注意力机制。
paper
这是一篇使用两种注意力机制的文章：
通道注意力机制
文中提到通道其实在分类时会起到不同作用，而使用通道注意力机制可以挖掘不用之间的相互依赖性空间注意力机制
空间注意力机制就是使模型更加关注图像中实体区域的贡献，减弱背景的影响。
主干网络以dilated FCN为主要结构：
在网络上使用如下两个注意力机制：
发现有大神进行了PPT讲解
一下类容来自冯爽朗。
以上内容都是截图。。。主要是为了偷懒。。。
源码：github
本人比较关注注意力机制。。。
在源码的encoding/nn/attention.py中发现注意力机制模块：
如下：
class PAM_Module(Module):
""" Position attention module"""
#Ref from SAGAN
def __init__(self, in_dim):
super(PAM_Module, self).__init__()
self.chanel_in = in_dim
self.query_conv = Conv2d(in_channels=in_dim, out_channels=in_dim//8, kernel_size=1)
self.key_conv = Conv2d(in_channels=in_dim, out_channels=in_dim//8, kernel_size=1)
self.value_conv = Conv2d(in_channels=in_dim, out_channels=in_dim, kernel_size=1)
self.gamma = Parameter(torch.zeros(1))
self.softmax = Softmax(dim=-1)
def forward(self, x):
"""
inputs :
x : input feature maps( B X C X H X W)
returns :
out : attention value + input feature
attention: B X (HxW) X (HxW)
"""
m_batchsize, C, height, width = x.size()
proj_query = self.query_conv(x).view(m_batchsize, -1, width*height).permute(0, 2, 1) # reshape to (m_batchsize, width*height, c)
proj_key = self.key_conv(x).view(m_batchsize, -1, width*height)
energy = torch.bmm(proj_query, proj_key) # 矩阵乘法
attention = self.softmax(energy) # 添加非线性函数
proj_value = self.value_conv(x).view(m_batchsize, -1, width*height)
out = torch.bmm(proj_value, attention.permute(0, 2, 1))
out = out.view(m_batchsize, C, height, width) # reshape到原图
out = self.gamma*out + x # 相加
return out
class CAM_Module(Module):
""" Channel attention module"""
def __init__(self, in_dim):
super(CAM_Module, self).__init__()
self.chanel_in = in_dim
self.gamma = Parameter(torch.zeros(1))
self.softmax = Softmax(dim=-1)
def forward(self,x):
"""
inputs :
x : input feature maps( B X C X H X W)
returns :
out : attention value + input feature
attention: B X C X C
"""
m_batchsize, C, height, width = x.size()
proj_query = x.view(m_batchsize, C, -1)
proj_key = x.view(m_batchsize, C, -1).permute(0, 2, 1)
energy = torch.bmm(proj_query, proj_key)
energy_new = torch.max(energy, -1, keepdim=True)[0].expand_as(energy)-energy
attention = self.softmax(energy_new)
proj_value = x.view(m_batchsize, C, -1)
out = torch.bmm(attention, proj_value)
out = out.view(m_batchsize, C, height, width)
out = self.gamma*out + x
return out
两个模块的融合在encoding/models/danet.py
中如下：
class DANetHead(nn.Module):
def __init__(self, in_channels, out_channels, norm_layer):
super(DANetHead, self).__init__()
inter_channels = in_channels // 4
self.conv5a = nn.Sequential(nn.Conv2d(in_channels, inter_channels, 3, padding=1, bias=False),
norm_layer(inter_channels),
nn.ReLU())
self.conv5c = nn.Sequential(nn.Conv2d(in_channels, inter_channels, 3, padding=1, bias=False),
norm_layer(inter_channels),
nn.ReLU())
self.sa = PAM_Module(inter_channels)
self.sc = CAM_Module(inter_channels)
self.conv51 = nn.Sequential(nn.Conv2d(inter_channels, inter_channels, 3, padding=1, bias=False),
norm_layer(inter_channels),
nn.ReLU())
self.conv52 = nn.Sequential(nn.Conv2d(inter_channels, inter_channels, 3, padding=1, bias=False),
norm_layer(inter_channels),
nn.ReLU())
self.conv6 = nn.Sequential(nn.Dropout2d(0.1, False), nn.Conv2d(512, out_channels, 1))
self.conv7 = nn.Sequential(nn.Dropout2d(0.1, False), nn.Conv2d(512, out_channels, 1))
self.conv8 = nn.Sequential(nn.Dropout2d(0.1, False), nn.Conv2d(512, out_channels, 1))
def forward(self, x):
feat1 = self.conv5a(x)
sa_feat = self.sa(feat1)
sa_conv = self.conv51(sa_feat)
sa_output = self.conv6(sa_conv)
feat2 = self.conv5c(x)
sc_feat = self.sc(feat2)
sc_conv = self.conv52(sc_feat)
sc_output = self.conv7(sc_conv)
feat_sum = sa_conv+sc_conv
sasc_output = self.conv8(feat_sum)
output = [sasc_output]
output.append(sa_output)
output.append(sc_output)
return tuple(output)
上面就是模型的融合，可以看到就是把两个模型进行逐元素相加操作。。
参考:
冯爽朗
