Affinity-aware Compression and Expansion Network for Human Parsing

TL;DR

This paper introduces ACENet, a novel human parsing network that addresses inter-part confusion and intra-part inconsistency through local compression and global expansion modules, achieving state-of-the-art results.

Contribution

The paper proposes ACENet with LCM and GEM modules, improving human parsing accuracy by enhancing structural and semantic relationships.

Findings

Achieves 58.1% mean IoU on LIP dataset.

Outperforms previous methods on human parsing benchmarks.

Effectively reduces inter-part interference and enhances intra-part consistency.

Abstract

As a fine-grained segmentation task, human parsing is still faced with two challenges: inter-part indistinction and intra-part inconsistency, due to the ambiguous definitions and confusing relationships between similar human parts. To tackle these two problems, this paper proposes a novel \textit{Affinity-aware Compression and Expansion} Network (ACENet), which mainly consists of two modules: Local Compression Module (LCM) and Global Expansion Module (GEM). Specifically, LCM compresses parts-correlation information through structural skeleton points, obtained from an extra skeleton branch. It can decrease the inter-part interference, and strengthen structural relationships between ambiguous parts. Furthermore, GEM expands semantic information of each part into a complete piece by incorporating the spatial affinity with boundary guidance, which can effectively enhance the semantic consistency of intra-part as well. ACENet achieves new state-of-the-art performance on the challenging LIP and Pascal-Person-Part datasets. In particular, 58.1% mean IoU is achieved on the LIP benchmark.