Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing

TL;DR

Grapy-ML introduces a hierarchical graph pyramid with mutual learning for improved cross-dataset human parsing, leveraging multi-granularity labels and self-attention to enhance feature discrimination.

Contribution

The paper proposes a novel graph pyramid module with mutual learning for cross-dataset human parsing, utilizing hierarchical structures and self-attention mechanisms.

Findings

Achieves state-of-the-art performance on CIHP dataset.

Effectively models multi-granularity labels for better feature learning.

Enables efficient mutual learning across datasets.

Abstract

Human parsing, or human body part semantic segmentation, has been an active research topic due to its wide potential applications. In this paper, we propose a novel GRAph PYramid Mutual Learning (Grapy-ML) method to address the cross-dataset human parsing problem, where the annotations are at different granularities. Starting from the prior knowledge of the human body hierarchical structure, we devise a graph pyramid module (GPM) by stacking three levels of graph structures from coarse granularity to fine granularity subsequently. At each level, GPM utilizes the self-attention mechanism to model the correlations between context nodes. Then, it adopts a top-down mechanism to progressively refine the hierarchical features through all the levels. GPM also enables efficient mutual learning. Specifically, the network weights of the first two levels are shared to exchange the learned coarse-granularity information across different datasets. By making use of the multi-granularity labels, Grapy-ML learns a more discriminative feature representation and achieves state-of-the-art performance, which is demonstrated by extensive experiments on the three popular benchmarks, e.g. CIHP dataset. The source code is publicly available at https://github.com/Charleshhy/Grapy-ML.