超越静态锚点：用于无语言医学异常检测的有界原型条件机制
Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection
浏览论文内容
中文总结 AI 辅助
本研究针对现有CLIP医学异常检测方法静态参考难以跨域迁移的问题，提出无语言框架ReCAP，通过有界门控调制的条件原型与非参数记忆实现异常检测，在多基准上性能最优且推理延迟大幅降低。
中文摘要 AI 辅助
医学异常检测在监督稀缺的情况下识别异常图像并定位病灶，同时实现跨器官与跨模态的泛化。现有基于CLIP的方法通过视觉-语言对齐降低标注需求，但其正常与异常参考（无论是文本提示还是学习得到的视觉令牌）在所有测试图像中保持固定。这种静态参考在跨域医学成像场景中可能无法可靠迁移至未见目标。为解决该问题，我们提出ReCAP，一个无语言框架，用输入条件化的视觉原型替代静态锚点。ReCAP通过有界门控调制为每张图像重新校准分离的正常与异常原型，实现查询自适应的异常评分，同时抑制上下文诱导的原型漂移。对于少样本设置，我们引入非参数正常参考记忆，以保留实例级目标域变化并补充条件原型分支。在六个医学基准上，ReCAP在所有零样本设置及24个少样本设置中的23个上取得最优图像级AUROC，且在所有三个分割数据集上取得最优零样本像素级AUROC。值得注意的是，与最快基线相比，它减少了70%以上的推理延迟，且无需文本提示或测试时梯度更新。
英文摘要
Medical anomaly detection identifies abnormal images and localizes lesions under scarce supervision while generalizing across organs and modalities. Existing CLIP-based methods reduce annotation requirements through vision--language alignment, but their normal and abnormal references, whether text prompts or learned visual tokens, remain fixed across test images. Such static references may not transfer reliably to unseen targets in a cross-domain medical imaging scenario. To address this, we propose ReCAP, a language-free framework that replaces static anchors with input-conditioned visual prototypes. ReCAP re-centers separated normal and abnormal prototypes for each image through a bounded gated modulation, enabling query-adaptive anomaly scoring while constraining context-induced prototype drift. For the few-shot setting, we introduce a non-parametric normal-reference memory to preserve instance-level target-domain variation and complement the conditional prototype branch. Across six medical benchmarks, ReCAP achieves the best image-level AUROC on all zero-shot and 23 of 24 few-shot settings, and the best zero-shot pixel-level AUROC on all three segmentation datasets. Particularly, it reduces inference latency by over 70% compared to the fastest baseline, without text prompts or test-time gradient updates.
