Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sahoo, Aadarsh, Gkioxari, Georgia
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911446785327104
author Sahoo, Aadarsh
Gkioxari, Georgia
author_facet Sahoo, Aadarsh
Gkioxari, Georgia
contents Conversational image segmentation grounds abstract, intent-driven concepts into pixel-accurate masks. Prior work on referring image grounding focuses on categorical and spatial queries (e.g., "left-most apple") and overlooks functional and physical reasoning (e.g., "where can I safely store the knife?"). We address this gap and introduce Conversational Image Segmentation (CIS) and ConverSeg, a benchmark spanning entities, spatial relations, intent, affordances, functions, safety, and physical reasoning. We also present ConverSeg-Net, which fuses strong segmentation priors with language understanding, and an AI-powered data engine that generates prompt-mask pairs without human supervision. We show that current language-guided segmentation models are inadequate for CIS, while ConverSeg-Net trained on our data engine achieves significant gains on ConverSeg and maintains strong performance on existing language-guided segmentation benchmarks. Project webpage: https://glab-caltech.github.io/converseg/
format Preprint
id arxiv_https___arxiv_org_abs_2602_13195
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision
Sahoo, Aadarsh
Gkioxari, Georgia
Computer Vision and Pattern Recognition
Conversational image segmentation grounds abstract, intent-driven concepts into pixel-accurate masks. Prior work on referring image grounding focuses on categorical and spatial queries (e.g., "left-most apple") and overlooks functional and physical reasoning (e.g., "where can I safely store the knife?"). We address this gap and introduce Conversational Image Segmentation (CIS) and ConverSeg, a benchmark spanning entities, spatial relations, intent, affordances, functions, safety, and physical reasoning. We also present ConverSeg-Net, which fuses strong segmentation priors with language understanding, and an AI-powered data engine that generates prompt-mask pairs without human supervision. We show that current language-guided segmentation models are inadequate for CIS, while ConverSeg-Net trained on our data engine achieves significant gains on ConverSeg and maintains strong performance on existing language-guided segmentation benchmarks. Project webpage: https://glab-caltech.github.io/converseg/
title Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.13195