无需训练，逐步细化分割结果，提升零样本图像语义分割精度
FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation
- 从粗到精分三步：去背景、定位目标、补全结构
- 1次和5次示例下，平均mIoU分别提升4.5和4.8点
- 适合需要快速部署的零样本分割场景
上下文分割（ICS）旨在仅凭一个或几个标注示例，精确分割任意语义概念（如物体或部分）。本文从经典分割视角重新审视ICS，将其视为由粗到精的渐进式优化过程。不直接通过参考-查询匹配预测最终掩码，而是逐步将模糊的前景响应细化为精确完整的前景结构。基于此思路，提出无需训练的上下文分割框架FoRIS，包含三个阶段：前景净化、前景定位与前景整合，分别抑制背景干扰、定位判别性区域、通过语义聚合恢复完整前景结构。实验表明，FoRIS在语义与部件分割任务上达到当前最优性能，在1次和5次示例设置下，平均mIoU分别相比现有方法提升4.5和4.8点。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。