FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation

Ming Hu; Jianfu Yin; Mingyu Dou; Miaomiao Zhang; Yao Wang; Cong Hu; Bingliang Hu; Quan Wang

cs.CVSep 3, 2026

FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation

Authors: Ming Hu, Jianfu Yin, Mingyu Dou, Miaomiao Zhang, Yao Wang, Cong Hu, Bingliang Hu, Quan Wang

Organizations: Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Xi’an Jiaotong University · Zhongnan Hospital of Wuhan University

Abstract

In-Context Segmentation (ICS) aims to precisely segment arbitrary semantic concepts, such as objects or parts, given one or a few annotated visual exemplars. In this paper, we revisit ICS from a more classical segmentation perspective, viewing it as a coarse-to-fine progressive refinement process. Rather than directly predicting the final mask through reference-query matching, we progressively refine the segmentation from coarse and ambiguous foreground responses to precise and complete foreground structures. Building upon this perspective, we propose a training-free in-context segmentation framework, termed FoRIS. Specifically, FoRIS consists of three key stages: Foreground Purification, Foreground Localization, and Foreground Consolidation, which progressively suppress background distractions, localize discriminative target regions, and recover complete foreground structures through semantic aggregation. Experimental results demonstrate that FoRIS achieves SOTA performance across semantic and part segmentation tasks, with average improvements of 4.5 and 4.8 mIoU points over existing approaches in the 1-shot and 5-shot settings, respectively. Code: https://github.com/Xi-Mu-Yu/FoRIS.

Explore similar work

Toward Robust In-Context Segmentation via Concept Guidance
Jun 26, 2026Zhigang Chen, Xiawu Zheng, Rongrong JiIn-Context Learning Vision-Language Model Grounding
REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation
Jul 10, 2026Mantha Sai Gopal, Jaison Saji Chacko, Harsh Nandwana +3Few-Shot Segmentation In-Context Learning
SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation
May 17, 2026Abderrahmene Boudiaf, Irfan Hussain, Sajid JavedTraining-Free Chain-Of-Thought Distillation

Jun 26, 2026 · cs.CVJ/K move · Enter open · S save

Toward Robust In-Context Segmentation via Concept Guidance

Zhigang Chen, Xiawu Zheng, Rongrong Ji

Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China

In-context segmentation (ICS) requires a model to segment target regions in a query image using only a few reference images and their corresponding masks, without updating any parameters. Despite recent progress, prior ICS studies have largely overlooked a critical aspect: system robustness, ie, whether the model can produce stable segmentation results for the same query under different references. In this work, we revisit ICS from the robustness perspective and introduce a novel paradigm, Concept-Guided In-Context Segmentation (CG-ICS), which performs segmentation by extracting high-level semantic concepts from references rather than relying solely on low-level visual matching. Specifically, CG-ICS introduces a concept reasoning module that uses an MLLM to propose candidates and a SAM3-driven scoring function with tree-search refinement to select reliable textual concepts, together with a parallel visual exemplar route that provides query-side spatial grounding via a simple context construction. Both the textual concept and the visual exemplar are then used to activate the segmentation capability of a frozen SAM3 backbone. Extensive experiments on standard ICS benchmarks demonstrate that CG-ICS not only achieves state-of-the-art accuracy but also substantially improves robustness, yielding a more reliable ICS system with significantly reduced variance across diverse reference choices. Code is available at https://github.com/Kakarot1103/CG-ICS.

In-Context Learning Vision-Language Model Grounding Spatial Grounding Single Images

Open paper Ask about it PDF

Abstract

Explore similar work

Toward Robust In-Context Segmentation via Concept Guidance

REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation

SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation