论文笔记——Factorized Convolutional Neural Networks
1. 论文思想
将3D卷积分解为spatial convolution in each channel and linear projection across channels.
(spatial convolution + linear projection.)
2. 两种卷积对比
3. 总结
简单概括就是spatial conv + linear projection,但是在spatial conv的时候用了一个residual connection,感觉很有道理,例如是一个vertical edge detector,那么horizontal information将丢失。这个和后来的MobileNet中的depthwise conv + pointwise conv非常的像。