Devil in the Details: Towards Accurate Single and Multiple Human Parsing

TL;DR

This paper introduces CE2P, a simple yet effective framework leveraging feature resolution, global context, and edge details for accurate human parsing, achieving state-of-the-art results on multiple benchmarks.

Contribution

The paper proposes the CE2P framework that effectively incorporates key properties for human parsing, setting new performance benchmarks and providing a solid baseline for future research.

Findings

Achieved top results on all three benchmarks with over 2% improvements.

Designed an end-to-end trainable model adaptable for single and multiple human parsing.

Outperformed previous methods significantly in mIoU and AP metrics.

Abstract

Human parsing has received considerable interest due to its wide application potentials. Nevertheless, it is still unclear how to develop an accurate human parsing system in an efficient and elegant way. In this paper, we identify several useful properties, including feature resolution, global context information and edge details, and perform rigorous analyses to reveal how to leverage them to benefit the human parsing task. The advantages of these useful properties finally result in a simple yet effective Context Embedding with Edge Perceiving (CE2P) framework for single human parsing. Our CE2P is end-to-end trainable and can be easily adopted for conducting multiple human parsing. Benefiting the superiority of CE2P, we achieved the 1st places on all three human parsing benchmarks. Without any bells and whistles, we achieved 56.50\% (mIoU), 45.31\% (mean $AP^r$) and 33.34\% ($AP^p_{0.5}$) in LIP, CIHP and MHP v2.0, which outperform the state-of-the-arts more than 2.06\%, 3.81\% and 1.87\%, respectively. We hope our CE2P will serve as a solid baseline and help ease future research in single/multiple human parsing. Code has been made available at \url{https://github.com/liutinglt/CE2P}.