【语义分割】 DRANet Scene Segmentation With Dual Relation-Aware Attention Network

接着上一篇博文介绍2019 CVPR DANet (Dual Attention Network for Scene Segmentation），这一篇DRANet可以看作是DANet进阶版，或者轻量化计算量版本。
原文中表述DANet的问题是虽然没有增加模型参数，但是每个点间和通道间的相关系数求解增加了模型的计算量和GPU内存使用

attention modeling brings a heavy burdern on computation and memory if the number of pixels/channels is huge

于是乎，由原来的relationship between any two pixels/channels(PAM/CAM)替换为relationship between any two pixel/channl and gathering centers(CPAM/CAM)模块。

Compact position attention module

相比PAM模块，CPAM主要增加了方框中的内容，目的就是降少计算量。方法：采用了不同尺度的pooling采样，标准像素子集的gathering centers。原文描述如下（可以学习一下如何把一个简单的下采样说得更高逼格）

construct the relationships between each pixel and a few numbers of gathering centers The gathering centers are formally defined as a compact feature vector by gathering feature vectors from a pixel subset in the input tensor. They are implemented by a spatial pyramid pooling scheme that provides context information from different spatial scales.

原文描述：

配合代码，通俗表达：

• 特征$\mathbf{A}\in {\mathbb{R}}^{C\times H\times W}$通过一组不同pooling
  kernel size的下采样后得到$L\times L{\mathbb{R}}^{C\times L^2}$大小的特征bin(图中的立方体的最小单元)，再将所有bin在通道层进行堆叠成$\mathbf{F}\in {\mathbb{R}}^{C\times M}$

代码对应encoding.nn.dran_att.CPAMEnc

class CPAMEnc(Module):
    """
    CPAM encoding module
    """
    def __init__(self, in_channels, norm_layer):
        super(CPAMEnc, self).__init__()
        self.pool1 = AdaptiveAvgPool2d(1)
        self.pool2 = AdaptiveAvgPool2d(2)
        self.pool3 = AdaptiveAvgPool2d(3)
        self.pool4 = AdaptiveAvgPool2d(6)

        self.conv1 = Sequential(Conv2d(in_channels, in_channels, 1, bias=False),
                                norm_layer(in_channels),
                                ReLU(True))
        self.conv2 = Sequential(Conv2d(in_channels, in_channels, 1, bias=False),
                                norm_layer(in_channels),
                                ReLU