Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Zhixiong, Li, Yizhuo, Ding, Shuangrui, Zang, Yuhang, Ding, Shengyuan, Xing, Long, Wang, Yibin, Zhang, Qiaosheng, Wang, Jiaqi
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.20110
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916028610510848
author Zhang, Zhixiong
Li, Yizhuo
Ding, Shuangrui
Zang, Yuhang
Ding, Shengyuan
Xing, Long
Wang, Yibin
Zhang, Qiaosheng
Wang, Jiaqi
author_facet Zhang, Zhixiong
Li, Yizhuo
Ding, Shuangrui
Zang, Yuhang
Ding, Shengyuan
Xing, Long
Wang, Yibin
Zhang, Qiaosheng
Wang, Jiaqi
contents Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-category groups, or open-ended target sets remains challenging. Previous Large Vision Language Model (LVLM)-based methods represent referred targets with one or more special tokens sequentially, treating multiple targets as separate outputs rather than a coherent set and offering little incentive to capture set-level properties such as completeness and mutual exclusivity. We reformulate open-ended referring segmentation as explicit set-level concept prediction and propose Set-Concept Segmentation (SetCon), which uses LVLM-generated natural-language concepts, instead of segmentation-specific tokens, as semantic conditions for joint mask-set decoding. A hierarchical semantic decomposition first predicts a shared set-level concept defining the target scope and then refines it into fine-grained concept groups aligned with target subsets. To support this, a two-stage annotation pipeline augments existing reasoning segmentation datasets with hierarchical semantic supervision (236k samples, 784k concept phrases). SetCon achieves state-of-the-art results on image benchmarks (+3.3 gIoU on gRefCOCO, +12.1 gIoU on MUSE), with margins that grow as the number of referred targets increases. The concept interface also transfers to video under a detect-and-track setting, yielding new state-of-the-art results on seven referring video benchmarks, including +10.9 J&F on MeViS and +12.4 J&F on Ref-SeCVOS.
format Preprint
id arxiv_https___arxiv_org_abs_2605_20110
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
Zhang, Zhixiong
Li, Yizhuo
Ding, Shuangrui
Zang, Yuhang
Ding, Shengyuan
Xing, Long
Wang, Yibin
Zhang, Qiaosheng
Wang, Jiaqi
Computer Vision and Pattern Recognition
Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-category groups, or open-ended target sets remains challenging. Previous Large Vision Language Model (LVLM)-based methods represent referred targets with one or more special tokens sequentially, treating multiple targets as separate outputs rather than a coherent set and offering little incentive to capture set-level properties such as completeness and mutual exclusivity. We reformulate open-ended referring segmentation as explicit set-level concept prediction and propose Set-Concept Segmentation (SetCon), which uses LVLM-generated natural-language concepts, instead of segmentation-specific tokens, as semantic conditions for joint mask-set decoding. A hierarchical semantic decomposition first predicts a shared set-level concept defining the target scope and then refines it into fine-grained concept groups aligned with target subsets. To support this, a two-stage annotation pipeline augments existing reasoning segmentation datasets with hierarchical semantic supervision (236k samples, 784k concept phrases). SetCon achieves state-of-the-art results on image benchmarks (+3.3 gIoU on gRefCOCO, +12.1 gIoU on MUSE), with margins that grow as the number of referred targets increases. The concept interface also transfers to video under a detect-and-track setting, yielding new state-of-the-art results on seven referring video benchmarks, including +10.9 J&F on MeViS and +12.4 J&F on Ref-SeCVOS.
title SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.20110