Progressive refinement: a method of coarse-to-fine image parsing using stacked network

TL;DR

This paper introduces a progressive coarse-to-fine image parsing method using stacked segmentation networks, which improves fine-grained semantic segmentation by hierarchical refinement and contextual information sharing.

Contribution

It proposes a novel stacked network architecture for coarse-to-fine image parsing, incorporating hierarchical supervision and skip connections for enhanced detail recovery.

Findings

Outperforms existing methods on face and human parsing datasets.

Effectively recovers small structural details with skip connections.

Demonstrates the versatility of the framework across multiple datasets.

Abstract

To parse images into fine-grained semantic parts, the complex fine-grained elements will put it in trouble when using off-the-shelf semantic segmentation networks. In this paper, for image parsing task, we propose to parse images from coarse to fine with progressively refined semantic classes. It is achieved by stacking the segmentation layers in a segmentation network several times. The former segmentation module parses images at a coarser-grained level, and the result will be feed to the following one to provide effective contextual clues for the finer-grained parsing. To recover the details of small structures, we add skip connections from shallow layers of the network to fine-grained parsing modules. As for the network training, we merge classes in groundtruth to get coarse-to-fine label maps, and train the stacked network with these hierarchical supervision end-to-end. Our coarse-to-fine stacked framework can be injected into many advanced neural networks to improve the parsing results. Extensive evaluations on several public datasets including face parsing and human parsing well demonstrate the superiority of our method.