掩码到概念：通过高效测试时概念嵌入搜索实现自动可提示的SAM3用于少样本标注
Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation
AI总结：
提出Mask to Concept (M2C)框架，无需外部模块或重训练，仅用少量标注图像，通过可学习概念嵌入搜索和混合不确定性估计，实现SAM3在医学图像中的自动少样本标注，达到SOTA性能。
摘要：
将基础分割模型从人工提示工具转变为自动可提示的标注器对于可扩展的医学数据标注至关重要。当前方法通常依赖外部特征匹配器或辅助网络来自动化几何提示，但这引入了架构开销并限制了性能可扩展性。尽管SAM3通过可重用的文本提示原生支持概念分割，但其在医学影像中的直接应用受到缺乏细粒度临床知识和人工描述模糊性的阻碍。在这项工作中，我们提出了Mask to Concept (M2C)，一种高效的框架，无需外部模块、参数重训练或手动文本工程，即可使SAM3适应医学少样本标注。仅使用少量标注图像，M2C使SAM3能够在其冻结架构内自动搜索可转移的视觉概念：它初始化一个可学习的概念嵌入，使用它来提示分割，并通过最小化概念分割误差的梯度来更新嵌入。我们进一步引入了混合不确定性估计（HUE）模块，该模块计算预测熵并将概念预测映射回框提示，从而衡量概念-几何提示的不一致性。高不确定性样本被主动标记以供人工修正，修正后的掩码随后反馈给M2C以持续搜索更精确的概念嵌入，形成一个需要最少专家努力的自增强标注循环。在医学分割基准上的实验表明，我们的方法实现了最先进的少样本分割性能和出色的标注效率，为可扩展的医学图像标注提供了一条实用且高效的途径。代码位于此https URL。
英文摘要：
Transforming foundation segmentation models from human-prompted tools into auto-promptable annotators is critical for scalable medical data annotation. Current methods commonly depend on external feature matchers or auxiliary networks to automate geometric prompting, but introducing architectural overhead and limiting performance scalability. Although SAM3 natively supports concept segmentation via reusable text prompts, its direct use in medical imaging is hindered by a lack of fine-grained clinical knowledge and the ambiguity of human-written descriptions. In this work, we propose Mask to Concept (M2C), an efficient framework that adapts SAM3 for medical few-shot annotation without external modules, parameter retraining, or manual text engineering. Using only a few labeled images, M2C enables SAM3 to automatically search for transferable visual concepts entirely within its frozen architecture: it initializes a learnable concept embedding, uses it to prompt segmentation, and updates the embedding by gradients of minimizing the concept segmentation error. We further introduce a Hybrid Uncertainty Estimation (HUE) module that calculates the prediction entropy and maps concept predictions back to the box prompts, measuring concept-geometry prompting inconsistency. Highly uncertain samples are flagged actively for human correction, and the corrected masks are then fed back to M2C to continuously search for more precise concept embeddings, forming a self-enhancing annotation loop with minimal expert effort. Experiments on medical segmentation benchmarks show that our method achieves SOTA few-shot segmentation performance and outstanding annotation efficiency, offering a practical and efficient pathway toward scalable medical image labeling. Codes are at https://github.com/Huster-Hq/M2C.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
