Squeeze-and-ExcitationNetworks流程图及其原理解析

介绍一下这个SE-Block,作者利用它获得了最后一届imageNet的冠军

论文链接：

https://arxiv.org/abs/1709.01507

GitHub：

https://github.com/hujie-frank/SENet

论文翻译:  https://blog.****.net/Quincuntial/article/details/78605463

 

 

 

The use of the whole SE-block is to ,   quoted from the paper:through which it can learn to use global information to selectively emphasise informative features and suppress less useful one.     

 

USAGE:the SE-Block can  directly replace other network block in the architecture , in other words, quote from the paper: SE blocks can also be used as a drop-in replacement for the original block at any depth in the architecture.

 

The SE-block can be divided into two parts(desite the orignal block part):Squeeze and Excitations

The goal for Squeeze action:  to exploit channel dependencies

How to squeeze:using global average pooling to generate channel-wise statistics,in other words,用global average pooling产生通道交互,as the details of squeeze are in the figure above.

The goal for Excitation operation :to fully capture channel-wise dependencies to make use of the information aggregated in the squeeze operation(利用好在squeeze操作中汇聚好的信息)

论文提到:activation作为适应input-specific feature descriptor 的channel weights。在这方面，SE-block本质上引入了以输入为条件的动态特性，helping to boost feature discriminability。这句话的意思...有待思考

 

The meaning behind the structure still remained to be found..

作者提到SE-block增强了网络的表征能力,by dynamic channel-wise feature重校准( recalibration),至于如何重校准(recalibration).把这个问题留到以后解决..

给以后留下的问题:每层网络这样干的原因..