想让模型在不同参考图下都稳定分割？试试 CG-ICS，用概念推理代替简单视觉匹配，SAM3 和 MLLM 帮你搞定。
CG-ICS 提出了一种概念引导的上下文分割方法，通过从参考图像中提取高层语义概念而非仅依赖低层视觉匹配来提升系统鲁棒性。该方法引入 MLLM 生成候选概念，并用 SAM3 驱动的评分函数和树搜索精炼选择可靠概念。同时并行视觉示例路径提供查询侧空间定位。在标准 ICS 基准测试上，CG-ICS 不仅达到最高精度，还将不同参考下的分割方差显著降低。
Toward Robust In-Context Segmentation via Concept Guidance
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.