Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Yuting, Jiang, Haichao, Liang, Tianming, Zhang, Quan, Hu, Jian-Fang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918519850926080
author Yang, Yuting
Jiang, Haichao
Liang, Tianming
Zhang, Quan
Hu, Jian-Fang
author_facet Yang, Yuting
Jiang, Haichao
Liang, Tianming
Zhang, Quan
Hu, Jian-Fang
contents Referring segmentation aims to segment the target objects in images or videos based on the textual query. Despite remarkable progress over the past years, existing works always assume that the user-provided queries are already precise and clear. However, this assumption is impractical. In real-world scenarios, it is unrealistic to expect all users to thoroughly review their visual content and carefully ensure their queries are unique and unambiguous. When encountering such cases, existing segmentation models tend to arbitrarily guess the user preferences, often resulting in undesired outcomes. To address this limitation, we propose IC-Seg, a novel agentic framework that proactively clarifies user intent through multi-turn conversation before segmentation. To effectively incentivize this capability, we further introduce Hi-GRPO, a new hierarchical optimization strategy that injects dense and informative supervision signals at the trajectory, turn, and step levels. This strategy encourages efficient intent clarification, effectively eliminating redundant interactions and improving overall dialogue quality. For evaluation, we establish Ambi-RVOS, a referring video object segmentation benchmark with ambiguous user queries. Extensive experiments demonstrate that IC-Seg not only outperforms existing methods by a large margin in resolving ambiguous queries, but also maintains state-of-the-art performance on standard reasoning segmentation benchmarks. Code and data will be released at https://github.com/iSEE-Laboratory/IC-Seg.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17531
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification
Yang, Yuting
Jiang, Haichao
Liang, Tianming
Zhang, Quan
Hu, Jian-Fang
Computer Vision and Pattern Recognition
Referring segmentation aims to segment the target objects in images or videos based on the textual query. Despite remarkable progress over the past years, existing works always assume that the user-provided queries are already precise and clear. However, this assumption is impractical. In real-world scenarios, it is unrealistic to expect all users to thoroughly review their visual content and carefully ensure their queries are unique and unambiguous. When encountering such cases, existing segmentation models tend to arbitrarily guess the user preferences, often resulting in undesired outcomes. To address this limitation, we propose IC-Seg, a novel agentic framework that proactively clarifies user intent through multi-turn conversation before segmentation. To effectively incentivize this capability, we further introduce Hi-GRPO, a new hierarchical optimization strategy that injects dense and informative supervision signals at the trajectory, turn, and step levels. This strategy encourages efficient intent clarification, effectively eliminating redundant interactions and improving overall dialogue quality. For evaluation, we establish Ambi-RVOS, a referring video object segmentation benchmark with ambiguous user queries. Extensive experiments demonstrate that IC-Seg not only outperforms existing methods by a large margin in resolving ambiguous queries, but also maintains state-of-the-art performance on standard reasoning segmentation benchmarks. Code and data will be released at https://github.com/iSEE-Laboratory/IC-Seg.
title Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.17531