Saved in:
Bibliographic Details
Main Authors: Chu, Jiaming, Jin, Lei, Xing, Junliang, Zhao, Jian
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2304.11356
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910451731791872
author Chu, Jiaming
Jin, Lei
Xing, Junliang
Zhao, Jian
author_facet Chu, Jiaming
Jin, Lei
Xing, Junliang
Zhao, Jian
contents This work studies the multi-human parsing problem. Existing methods, either following top-down or bottom-up two-stage paradigms, usually involve expensive computational costs. We instead present a high-performance Single-stage Multi-human Parsing (SMP) deep architecture that decouples the multi-human parsing problem into two fine-grained sub-problems, i.e., locating the human body and parts. SMP leverages the point features in the barycenter positions to obtain their segmentation and then generates a series of offsets from the barycenter of the human body to the barycenters of parts, thus performing human body and parts matching without the grouping process. Within the SMP architecture, we propose a Refined Feature Retain module to extract the global feature of instances through generated mask attention and a Mask of Interest Reclassify module as a trainable plug-in module to refine the classification results with the predicted segmentation. Extensive experiments on the MHPv2.0 dataset demonstrate the best effectiveness and efficiency of the proposed method, surpassing the state-of-the-art method by 2.1% in AP50p, 1.0% in APvolp, and 1.2% in PCP50. In particular, the proposed method requires fewer training epochs and a less complex model architecture. We will release our source codes, pretrained models, and online demos to facilitate further studies.
format Preprint
id arxiv_https___arxiv_org_abs_2304_11356
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Single-stage Multi-human Parsing via Point Sets and Center-based Offsets
Chu, Jiaming
Jin, Lei
Xing, Junliang
Zhao, Jian
Computer Vision and Pattern Recognition
This work studies the multi-human parsing problem. Existing methods, either following top-down or bottom-up two-stage paradigms, usually involve expensive computational costs. We instead present a high-performance Single-stage Multi-human Parsing (SMP) deep architecture that decouples the multi-human parsing problem into two fine-grained sub-problems, i.e., locating the human body and parts. SMP leverages the point features in the barycenter positions to obtain their segmentation and then generates a series of offsets from the barycenter of the human body to the barycenters of parts, thus performing human body and parts matching without the grouping process. Within the SMP architecture, we propose a Refined Feature Retain module to extract the global feature of instances through generated mask attention and a Mask of Interest Reclassify module as a trainable plug-in module to refine the classification results with the predicted segmentation. Extensive experiments on the MHPv2.0 dataset demonstrate the best effectiveness and efficiency of the proposed method, surpassing the state-of-the-art method by 2.1% in AP50p, 1.0% in APvolp, and 1.2% in PCP50. In particular, the proposed method requires fewer training epochs and a less complex model architecture. We will release our source codes, pretrained models, and online demos to facilitate further studies.
title Single-stage Multi-human Parsing via Point Sets and Center-based Offsets
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.11356