UniParser: Multi-Human Parsing With Unified Correlation Representation Learning

Jiaming Chu

doi:10.1109/TIP.2024.3456004

UniParser: Multi-Human Parsing With Unified Correlation Representation Learning

2024-01-01

0

PRE

AI

DOI：10.1109/TIP.2024.3456004

Original

Original request for help

Save

Abstract

En 中文

Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically processed these two types of information through distinct branch types and output formats, leading to inefficient and redundant frameworks. This paper introduces UniParser, which integrates instance-level and category-level representations in three key aspects: 1) we propose a unified correlation representation learning approach, allowing our network to learn instance and category features within the cosine space; 2) we unify the form of outputs of each modules as pixel-level results while supervising instance and category features using a homogeneous label accompanied by an auxiliary loss; and 3) we design a joint optimization procedure to fuse instance and category representations. By unifying instance-level and category-level output, UniParser circumvents manually designed post-processing techniques and surpasses state-of-the-art methods, achieving 49.3% AP on MHPv2.0 and 60.4% AP on CIHP. We have released our source code, pretrained models, and demos to facilitate future studies on https://github.com/cjm-sfw/Uniparser.

Keywords:

Correlation

Feature extraction

Head

Convolution

Representation learning

Kernel

Semantics

multi-human parsing

instance segmentation

UniParser: Multi-Human Parsing With Unified Correlation Representation Learning

Abstract

Journal

Organization