Mean Field inference of CRFs based on GAT

TL;DR

This paper introduces a novel mean-field inference method for fully connected CRFs using graph attention networks, enabling efficient sequence annotation for tasks like image segmentation and text annotation.

Contribution

It replaces traditional message passing with graph attention operations, transforming inference into a GAT forward pass, and applies residual GATs to various sequence annotation tasks.

Findings

Achieves improved inference efficiency over traditional methods.

Applicable to both image segmentation and text annotation tasks.

Demonstrates competitive performance in sequence annotation.

Abstract

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.