残差注意力网络原理与应用分析

Attention not only serves to select a focused location but also enhances different representations of objects at that location.

Recent advances of image classification focus on training feedforward convolutional neural networks using “very deep” structure.

Inspired by the attention mechanism and recent advances in the deep neural network, we propose Residual Attention Network, a convolutional network that adopts mixed attention mechanism in “very deep” structure.

残差注意力网络由多个注意力模块组成，这些注意力模块产生注意力感知特征。不同模块的注意力感知特征随着层次的加深而自适应地变化。

直接堆叠注意力模块会导致显著的性能下降。因此，我们提出了注意力残差学习机制来优化数百层的极深层残差注意力网络。

网络结构

特征与注意力掩码的