Open-Vocabulary Part Segmentation via Progressive and Boundary-Aware Strategy
Xinlong Li, Di Lin, Shaoyiyi Gao, Jiaxin Li, Ruonan Liu, Qing Guo
Abstract
Open-vocabulary part segmentation (OVPS) struggles with structurally connected boundaries due to the inherent conflict between continuous image features and discrete classification mechanism. To address this, we propose PBAPS, a novel training-free framework specifically designed for OVPS. PBAPS leverages structural knowledge of object-part relationships to guide a progressive segmentation from objects to fine-grained parts. To further improve accuracy at challenging boundaries, we introduce a Boundary-Aware Refinement (BAR) module that identifies ambiguous boundary regions by quantifying classification uncertainty, enhances the discriminative features of these ambiguous regions using high-confidence context, and adaptively refines part prototypes to better align with the specific image. Experiments on Pascal-Part-116, ADE20K-Part-234, PartImageNet demonstrate that PBAPS significantly outperforms state-of-the-art methods, achieving 46.35\% mIoU and 34.46\% bIoU on Pascal-Part-116. Our code is available at https://github.com/TJU-IDVLab/PBAPS.
BibTeX
@inproceedings{
li2025openvocabulary,
title={Open-Vocabulary Part Segmentation via Progressive and Boundary-Aware Strategy},
author={Xinlong Li and Di Lin and Shaoyiyi Gao and Jiaxin Li and Ruonan Liu and Qing Guo},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=gwT1GOKiaO}
}