SE-Net整理阅读

最近算是好不容易抽时间把这SE-Net论文看完了，总体来说收获还是很多的，以下是自己的一些理解和整理。

SE-Net的整体思路

引入了注意力的思想，即对于每个通道，用一个权重来表示该通道在下一阶段的重要性;

做成了一个插入式的模块，十分方便与各个基础网络的结合。

Introduction部分

这部分作者总结了CNN神经网络效果显著的原因：原文如下：

At each convolutional layer in the network, a collection of filters expresses neighbourhood spatial connectivity patterns along input channels—fusing spatial and channel-wise information together within local receptive fields. By interleaving a series of convolutional layers with non-linear activation functions and downsam- pling operators, CNNs are able to produce robust represen- tations that capture hierarchical patterns and attain global theoretical receptive fields. Recent research has shown that these representations can be strengthened by integrating learning mechanisms into the network that help capture spatial correlations between features. One such approach, popularised by the Inception family of architectures [5], [6], incorporates multi-scale processes into network modules to achieve improved performance. Further work has sought to better model spatial dependencies [7], [8] and incorporate spatial attention into the structure of the network [9].

总结起来如下：

滤波器(filter)通过局部的感受野将特征图的空间(spatial)和深度(depth-wise)上的信息进行融合;

通过一系列的卷积层来学习层级的样式(pattern)和全局的感受野;

通过将学习机制整合到网络中可以增强这些表达能力，这有助于捕获特征之间的空间相关性;