Quality-Aware Network for Face Parsing

TL;DR

This paper presents a face parsing method that applies state-of-the-art human parsing techniques, achieving high accuracy and competitive results in a CVPR challenge.

Contribution

It explores the application of human parsing methods to face parsing, demonstrating their effectiveness and differences in this specific task.

Findings

Achieved 86.84% score in face parsing challenge

Secured 2nd place in the CVPR 2021 challenge

Highlights similarities between face and human parsing tasks

Abstract

This is a very short technical report, which introduces the solution of the Team BUPT-CASIA for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. Face parsing has recently attracted increasing interest due to its numerous application potentials. Generally speaking, it has a lot in common with human parsing, such as task setting, data characteristics, number of categories and so on. Therefore, this work applies state-of-the-art human parsing method to face parsing task to explore the similarities and differences between them. Our submission achieves 86.84% score and wins the 2nd place in the challenge.