PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs

• URL: http://arxiv.org/abs/2606.20913v1
• Date: Thu, 18 Jun 2026 20:09:13 GMT
• Title: PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs
• Abstract summary: Out-of-distribution (OOD) inputs at deployment remain an open problem for medical vision-language models (VLMs)<n>We propose PROTON (PROtotype-based Test-time ONline OOD detection), a lightweight post-hoc module that fuses prototype distance with OOD scoring via stream-level variance statistics.<n>On the benchmark FLAIR + FIVES, PROTON improves MCM by +23.9 AUROC on covariate shift, +8.8 on semantic shift, and +8.1 on far-OOD, making it the only zero-shot method to improve all three without hierarchical prompts or labeled data.
• Score: 26.105088397249034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Medical vision-language models (VLMs) enable zero-shot clinical image classification, yet reliably detecting out-of-distribution (OOD) inputs at deployment remains an open problem. No static scoring method works across all shift types: Maximum Concept Matching (MCM) on FLAIR achieves 76.4% AUROC for far-OOD but only 42.4% for covariate shifts such as ultra-wide-field fundus images, effectively random. We trace this to a structural mismatch: covariate-shifted inputs are indistinguishable from in-distribution samples in softmax space, yet occupy distinct regions in the VLM embedding space. To exploit this untapped signal, we propose PROTON (PROtotype-based Test-time ONline OOD detection), a lightweight post-hoc module that maintains an online prototype bank from high-confidence test predictions and adaptively fuses prototype distance with MCM scoring via stream-level variance statistics, requiring no model modification, training data, or prompt engineering. On the ophthalmology benchmark FLAIR + FIVES, PROTON improves MCM by +23.9 AUROC on covariate shift, +8.8 on semantic shift, and +8.1 on far-OOD, making it the only zero-shot method to improve all three without hierarchical prompts or labeled data. Code is available at https://github.com/GenMI-Lab/PROTON, and the project page is available at https://genmi-lab.github.io/PROTON.

Related papers

• Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation [95.55552104238787]
  Test-Time Adaptation (TTA) methods aim to bridge the domain gap between the source and target domains.<n>Traditional TTA methods become ineffective when the label distribution shift occurs.<n>We introduce a new method named Reliable Neural Collapse approximation (ReNC) for Open-World Test-Time Adaptation.
  arXiv  Detail & Related papers  (2026-08-20T10:57:44Z)
• LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation [73.21089889761498]
  Source-free universal domain adaptation (SF-UniDA) adapts a pre-trained source model to an unlabeled target domain.<n>We propose a framework that leverages foundation models (LFM) for SF-UniDA.
  arXiv  Detail & Related papers  (2026-07-20T08:06:44Z)
• Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detection [0.8394724589095839]
  We show that intermediate layers encode equally rich and discriminative information for OOD detection.<n>We propose a model-agnostic approach that leverages internal representations across multiple layers.<n>Our approach delivers robust, architecture-agnostic performance and strong generalization for image classification.
  arXiv  Detail & Related papers  (2026-03-24T19:32:13Z)
• ProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Models [32.840734752367275]
  Prototype-based Double-Check Separation (ProtoDCS) is a robust framework for OSTTA.<n>It separates csID and csOOD samples, enabling safe and efficient adaptation of Vision-Language Models to csID data.<n>ProtoDCS significantly boosts both known-class accuracy and OOD detection metrics.
  arXiv  Detail & Related papers  (2026-02-27T03:39:02Z)
• Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving [7.064497253920508]
  Vision Foundation Models (VFMs) as feature extractors and density modeling techniques are proposed.<n>A comparison with state-of-the-art binary OOD classification methods reveals that VFM embeddings with density estimation outperform existing approaches in identifying OOD inputs.<n>Our method detects high-risk inputs likely to cause errors in downstream tasks, thereby improving overall performance.
  arXiv  Detail & Related papers  (2025-01-14T12:51:34Z)
• DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection [11.332987462182713]
  In adversarial discriminators trained with Batch Normalization (BN), real and adversarial samples form distinct domains with unique batch statistics.<n>We introduce DisCoPatch, an unsupervised Adversarial Variational Autoencoder framework that harnesses this mechanism.<n>DisCoPatch achieves state-of-the-art results in public OOD detection benchmarks.
  arXiv  Detail & Related papers  (2025-01-14T10:49:26Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• Test-Time Model Adaptation with Only Forward Passes [68.11784295706995]
  Test-time adaptation has proven effective in adapting a given trained model to unseen test samples with potential distribution shifts. We propose a test-time Forward-Optimization Adaptation (FOA) method. FOA runs on quantized 8-bit ViT, outperforms gradient-based TENT on full-precision 32-bit ViT, and achieves an up to 24-fold memory reduction on ImageNet-C.
  arXiv  Detail & Related papers  (2024-04-02T05:34:33Z)
• Towards Reliable AI Model Deployments: Multiple Input Mixup for Out-of-Distribution Detection [4.985768723667418]
  We propose a novel and simple method to solve the Out-of-Distribution (OOD) detection problem. Our method can help improve the OOD detection performance with only single epoch fine-tuning. Our method does not require training the model from scratch and can be attached to the classifier simply.
  arXiv  Detail & Related papers  (2023-12-24T15:31:51Z)
• Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability [70.72426887518517]
  Out-of-distribution (OOD) detection is an indispensable aspect of secure AI when deploying machine learning models in real-world applications. We propose a novel method, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data. Our method utilizes a mask to figure out the memorized atypical samples, and then finetune the model or prune it with the introduced mask to forget them.
  arXiv  Detail & Related papers  (2023-06-06T14:23:34Z)
• Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models [76.410400238974]
  We propose TTA with feedback to rectify the model output and prevent the model from becoming blindly confident. A CLIP model is adopted as the reward model during TTA and provides feedback for the VLM. The proposed textitreinforcement learning with CLIP feedback(RLCF) framework is highly flexible and universal.
  arXiv  Detail & Related papers  (2023-05-29T11:03:59Z)
• UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models [92.43617471204963]
  Diffusion probabilistic models (DPMs) have demonstrated a very promising ability in high-resolution image synthesis. We develop a unified corrector (UniC) that can be applied after any existing DPM sampler to increase the order of accuracy. We propose a unified predictor-corrector framework called UniPC for the fast sampling of DPMs.
  arXiv  Detail & Related papers  (2023-02-09T18:59:48Z)
• DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows [52.31831255787147]
  We introduce a novel technique, DAAIN, to detect out-of-distribution (OOD) inputs and adversarial attacks (AA) Our approach monitors the inner workings of a neural network and learns a density estimator of the activation distribution. Our model can be trained on a single GPU making it compute efficient and deployable without requiring specialized accelerators.
  arXiv  Detail & Related papers  (2021-05-30T22:07:13Z)
• Contextual-Bandit Anomaly Detection for IoT Data in Distributed Hierarchical Edge Computing [65.78881372074983]
  IoT devices can hardly afford complex deep neural networks (DNN) models, and offloading anomaly detection tasks to the cloud incurs long delay. We propose and build a demo for an adaptive anomaly detection approach for distributed hierarchical edge computing (HEC) systems. We show that our proposed approach significantly reduces detection delay without sacrificing accuracy, as compared to offloading detection tasks to the cloud.
  arXiv  Detail & Related papers  (2020-04-15T06:13:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.