Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| 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 |