发表机构
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（中国科学院西安光学精密机械研究所; 中国科学院大学; 西安交通大学; 武汉大学中南医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对上下文内分割任务提出无需训练的FoRIS框架，通过前景纯化、定位、整合三阶段渐进细化实现SOTA性能，1次和5次设置下mIoU较现有方法分别提升4.5、4.8点。
AI 中文摘要
上下文内分割（ICS）旨在给定一个或几个带注释的视觉示例的情况下，精确分割任意语义概念，例如对象或部件。在本文中，我们从更经典的分割视角重新审视ICS，将其视为一个由粗到细的渐进式细化过程。我们并非通过参考-查询匹配直接预测最终掩码，而是从粗糙且模糊的前景响应逐步细化到精确且完整的前景结构。基于这一视角，我们提出了一种名为FoRIS的无需训练的上下文内分割框架。具体而言，FoRIS包含三个关键阶段：前景纯化、前景定位和前景整合，通过语义聚合逐步抑制背景干扰、定位具有判别性的目标区域并恢复完整的前景结构。实验结果表明，FoRIS在语义和部件分割任务上实现了SOTA性能，在1次和5次设置下，相比现有方法分别取得了4.5和4.8 mIoU点的平均提升。代码：this https URL。
英文摘要
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.
