A Branching Network for Human Parsing Based on Quantifying Background-Part Relationships *

Human parsing is a critical computer vision task that involves segmenting and labeling body parts in images. Due to variations in human poses and clothing, designing effective parsing algorithms is challenging. This paper examines how background impacts parsing results and proposes grouping body parts based on mutual information with the background. We introduce an end-to-end replacement-concatenation network to enhance existing methods and a branching network that refines feature sharing to reduce negative interactions and improve feature learning for different body parts. Experimental results show a significant improvement in parsing effectiveness using our approach.