![](https://img-blog.csdnimg.cn/20201014180756927.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
Decoupled Learning
文章平均质量分 92
Trasper1
The future awaits
展开
-
CVPR2018 Spotlight 《Decoupled Networks》读后感
首先要明确的最顶层的概念是:CNN是一个visual representation learning的过程,所有的convolutional filters wi是学到的features template,每一个convolutional操作就是一个template matching,通过dot-product这种计算方式来量化滑窗位置的image patch xi与convolutional f...原创 2018-12-01 16:32:18 · 747 阅读 · 0 评论 -
2017 NIPS《Deep Hyperspherical Learning》读后感
本文提出的是一个极其顶层的深度学习概念:Learning with angular information between w and x on Hyperspheres。本着这个精神,作者提出了SphereConve,depend on which SphereNet is established,which is then trained with Angualr Softmax loss。...原创 2018-12-01 21:25:47 · 679 阅读 · 0 评论