Log In Sign Up

Mean Field inference of CRFs based on GAT

by   LingHong Xing, et al.

In this paper we propose an improved mean-field inference algorithm for the fully connected paired CRFs model. The improved method Message Passing operation is changed from the original linear convolution to the present graph attention operation, while the process of the inference algorithm is turned into the forward process of the GAT model. Combined with the mean-field inferred label distribution, it is equivalent to the output of a classifier with only unary potential. To this end, we propose a graph attention network model with residual structure, and the model approach is applicable to all sequence annotation tasks, such as pixel-level image semantic segmentation tasks as well as text annotation tasks.


page 1

page 2

page 3

page 4


Mean-Field Networks

The mean field algorithm is a widely used approximate inference algorith...

Dilated Continuous Random Field for Semantic Segmentation

Mean field approximation methodology has laid the foundation of modern C...

On the role of solute drag in reconciling laboratory and natural constraints on olivine grain growth kinetics

We investigate the effect of solute drag on grain growth (GG) kinetics i...

Mean Field Analysis of Personalized PageRank with Implications for Local Graph Clustering

We analyse a mean-field model of Personalized PageRank on the Erdos-Reny...

Mean-field inference methods for neural networks

Machine learning algorithms relying on deep neural networks recently all...

Mean Field Network based Graph Refinement with application to Airway Tree Extraction

We present tree extraction in 3D images as a graph refinement task, of o...

A Factorized Variational Technique for Phase Unwrapping in Markov Random Fields

Some types of medical and topographic imaging device produce images in w...