Saved in:
Bibliographic Details
Main Authors: Dutta, Arindam, Lal, Rohit, Garg, Yash, Ta, Calvin-Khang, Raychaudhuri, Dripta S., Cruz, Hannah Dela, Roy-Chowdhury, Amit K.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.03549
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910538784571392
author Dutta, Arindam
Lal, Rohit
Garg, Yash
Ta, Calvin-Khang
Raychaudhuri, Dripta S.
Cruz, Hannah Dela
Roy-Chowdhury, Amit K.
author_facet Dutta, Arindam
Lal, Rohit
Garg, Yash
Ta, Calvin-Khang
Raychaudhuri, Dripta S.
Cruz, Hannah Dela
Roy-Chowdhury, Amit K.
contents Existing algorithms for human body part segmentation have shown promising results on challenging datasets, primarily relying on end-to-end supervision. However, these algorithms exhibit severe performance drops in the face of domain shifts, leading to inaccurate segmentation masks. To tackle this issue, we introduce POSTURE: \underline{Po}se Guided Un\underline{s}upervised Domain Adap\underline{t}ation for H\underline{u}man Body Pa\underline{r}t S\underline{e}gmentation - an innovative pseudo-labelling approach designed to improve segmentation performance on the unlabeled target data. Distinct from conventional domain adaptive methods for general semantic segmentation, POSTURE stands out by considering the underlying structure of the human body and uses anatomical guidance from pose keypoints to drive the adaptation process. This strong inductive prior translates to impressive performance improvements, averaging 8\% over existing state-of-the-art domain adaptive semantic segmentation methods across three benchmark datasets. Furthermore, the inherent flexibility of our proposed approach facilitates seamless extension to source-free settings (SF-POSTURE), effectively mitigating potential privacy and computational concerns, with negligible drop in performance.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03549
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle POSTURE: Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentation
Dutta, Arindam
Lal, Rohit
Garg, Yash
Ta, Calvin-Khang
Raychaudhuri, Dripta S.
Cruz, Hannah Dela
Roy-Chowdhury, Amit K.
Computer Vision and Pattern Recognition
Existing algorithms for human body part segmentation have shown promising results on challenging datasets, primarily relying on end-to-end supervision. However, these algorithms exhibit severe performance drops in the face of domain shifts, leading to inaccurate segmentation masks. To tackle this issue, we introduce POSTURE: \underline{Po}se Guided Un\underline{s}upervised Domain Adap\underline{t}ation for H\underline{u}man Body Pa\underline{r}t S\underline{e}gmentation - an innovative pseudo-labelling approach designed to improve segmentation performance on the unlabeled target data. Distinct from conventional domain adaptive methods for general semantic segmentation, POSTURE stands out by considering the underlying structure of the human body and uses anatomical guidance from pose keypoints to drive the adaptation process. This strong inductive prior translates to impressive performance improvements, averaging 8\% over existing state-of-the-art domain adaptive semantic segmentation methods across three benchmark datasets. Furthermore, the inherent flexibility of our proposed approach facilitates seamless extension to source-free settings (SF-POSTURE), effectively mitigating potential privacy and computational concerns, with negligible drop in performance.
title POSTURE: Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.03549