论文：https://arxiv.org/pdf/2010.03045.pdf

本文提出了可以有效解决跨维度交互的triplet attention。相较于以往的注意力方法，主要有两个优点：

1.可以忽略的计算开销

2.强调了多维交互而不降低维度的重要性，因此消除了通道和权重之间的间接对应。

        传统的计算通道注意力的方法为了计算这些通道的权值，输入张量在空间上通过全局平均池化分解为一个像素。这导致了空间信息的大量丢失，因此在单像素通道上计算注意力时，通道维数和空间维数之间的相互依赖性也不存在。后面提出基于Spatial和Channel的CBAM模型缓解了空间相互依赖的问题，但是通道注意和空间注意是分离的，计算是相互独立的。基于建立空间注意力的方法，本文提出了跨维度交互作用(cross dimension interaction)的概念，通过捕捉空间维度和输入张量通道维度之间的交互作用，解决了这一问题。

 

 

        所提出的Triplet Attention如下图所示，Triplet Attention由3个平行的Branch组成，其中两个负责捕获通道C和空间H或W之间的跨维交互。最后一个Branch类似于CBAM，用于构建Spatial Attention，最终3个Branch的输出使用平均求和。

 效果优于CBAM、SE

 

 2.Triplet加入Yolov5

2.1Triple加入common.py

###################### TripletAttention  ####     start   by  AI&CV  ###############################

class BasicConv(nn.Module):   #https://arxiv.org/pdf/2010.03045.pdf
    def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True,
                 bn=True, bias=False):
        super(BasicConv, self).__init__()
        self.out_channels = out_planes
        self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding,
                              dilation=dilation, groups=groups, bias=bias)
        self.bn = nn.BatchNorm2d(out_planes, eps=1e-5, momentum=0.01, affine=True) if bn else None
        self.relu = nn.ReLU() if relu else None

    def forward(self, x):
        x = self.conv(x)
        if self.bn is not None:
            x = self.bn(x)
        if self.relu is not None:
            x = self.relu(x)
        return x


class ZPool(nn.Module):
    def forward(self, x):
        return torch.cat((torch.max(x, 1)[0].unsqueeze(1), torch.mean(x, 1).unsqueeze(1)), dim=1)


class AttentionGate(nn.Module):
    def __init__(self):
        super(AttentionGate, self).__init__()
        kernel_size = 7
        self.compress = ZPool()
        self.conv = BasicConv(2, 1, kernel_size, stride=1, padding=(kernel_size - 1) // 2, relu=False)

    def forward(self, x):
        x_compress = self.compress(x)
        x_out = self.conv(x_compress)
        scale = torch.sigmoid_(x_out)
        return x * scale


class TripletAttention(nn.Module):
    def __init__(self, no_spatial=False):
        super(TripletAttention, self).__init__()
        self.cw = AttentionGate()
        self.hc = AttentionGate()
        self.no_spatial = no_spatial
        if not no_spatial:
            self.hw = AttentionGate()

    def forward(self, x):
        x_perm1 = x.permute(0, 2, 1, 3).contiguous()
        x_out1 = self.cw(x_perm1)
        x_out11 = x_out1.permute(0, 2, 1, 3).contiguous()
        x_perm2 = x.permute(0, 3, 2, 1).contiguous()
        x_out2 = self.hc(x_perm2)
        x_out21 = x_out2.permute(0, 3, 2, 1).contiguous()
        if not self.no_spatial:
            x_out = self.hw(x)
            x_out = 1 / 3 * (x_out + x_out11 + x_out21)
        else:
            x_out = 1 / 2 * (x_out11 + x_out21)
        return x_out

###################### TripletAttention  ####     END   by  AI&CV  ###############################

2.2Triple加入yolo.py

def parse_model(d, ch): 加入以下代码

        elif m is TripletAttention:
            c1, c2 = ch[f], args[0]
            if c2 != no:
                c2 = make_divisible(c2 * gw, 8)
            args = [c1, *args[1:]]

2.3 修改yolov5s_TripletAttention.yaml

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# Parameters
nc: 6  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
   [-1, 1, TripletAttention,[1024]],   # 23 (P5/32-large)

   [[17, 20, 24], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]