# Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection

arXiv: https://arxiv.org/abs/2608.00442 · HTML: https://mlsanity.com/paper/2608.00442/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [Adversarially Learned One-Class Classifier for Novelty Detection](https://mlsanity.com/paper/1802.09088/) (2018)
- [Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection](https://mlsanity.com/paper/2203.14506/) (2022)
- [AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP](https://mlsanity.com/paper/2503.06661/) (2025)
- [One-for-More: Continual Diffusion Model for Anomaly Detection](https://mlsanity.com/paper/2502.19848/) (2025)
- [VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer](https://mlsanity.com/paper/2603.07952/) (2026)
- [Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection](https://mlsanity.com/paper/2502.20981/) (2025)
- [MadCLIP: Few-shot Medical Anomaly Detection with CLIP](https://mlsanity.com/paper/2506.23810/) (2025)
- [UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation](https://mlsanity.com/paper/2506.19694/) (2025)
- [One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection](https://mlsanity.com/paper/2601.05552/) (2026)
- [IQE-CLIP: Instance-aware Query Embedding for Zero-/Few-shot Anomaly Detection in Medical Domain](https://mlsanity.com/paper/2506.10730/) (2025)

## Abstract (arXiv)

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.