语义分割进阶之路之回首CVPR2016（三）

Gaussian Conditional Random Field Network for Semantic Segmentation. 

Raviteja Vemulapalli, Oncel Tuzel, Ming-Yu Liu, Rama Chellapa

 

这篇论文很有意义的，我们知道2015的cvpr对语义分割的方法局限于，场\概率、超像素、FCN这三种

本文就是在“场”这个方向进发，涉及了很多“场”的问题。使用了GCRF代替CRF，并且他自己设计了一套流程听说效果是很不错的。

 

abstract
In contrast to the existing approaches that use discrete Conditional Random Field (CRF) models, we propose to use a Gaussian CRF model for the task of semantic segmentation. We propose a novel deep network, which we refer to as Gaussian Mean Field (GMF) network, whose layers perform mean field inference over a Gaussian CRF. The proposed GMF network has the desired property that each of its layers produces an outp