MARVEL: Margin-Aware Robust von Mises-Fischer Expert Learning for Long-Tailed Out-of-Distribution Detection
2026-07-02 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method to help medical AI systems better recognize when they encounter unfamiliar cases, which is important for real-world use. Their approach uses a special classifier that learns complex patterns and includes multiple experts that focus on different parts of the data, especially when the data is unbalanced. They also added a component specifically trained to spot unusual or outlier cases. Tested on several medical datasets, their method showed clear improvements in detecting unfamiliar cases compared to previous techniques, helping AI tools safely defer tricky cases to human doctors.
Out-of-distribution detectionNonlinear von Mises-Fisher classifierImbalanced datasetsMulti-expert frameworkMargin-aware classificationMedical image datasetsAI-assisted diagnosisFalse Positive Rate (FPR95)Outlier detection
Authors
A. S. Anudeep, Vaanathi Sundaresan
Abstract
For clinical deployment, it is essential that automated diagnostic systems remain reliable when confronted with previously unseen cases, yet deep models routinely misclassify out-of-distribution (OOD) inputs with high confidence, underscoring the need for more robust OOD detection methods. Although substantial effort has been devoted to improving model robustness, most of the existing literature assumes balanced datasets, evaluates OOD detection on coarse or non-clinical OOD sources, or lacks comprehensive assessment across diverse OOD scenarios. To address the gaps, we propose a novel methodology trained on diverse and imbalanced medical datasets and evaluated across a clinically reflective OOD spectrum. Our framework comprises three key components: (1) a Nonlinear von Mises-Fisher (NvMF) classifier capable of learning non-linear decision boundaries, with theoretical proof of its asymptotic connection to cosine classifiers; (2) a multi-expert framework in which margin-aware NvMF classifiers specialise in different regions of label distribution to better handle imbalance; and (3) an outlier expert trained explicitly to distinguish inlier from outlier data, thereby strengthening OOD detection. Evaluation on RFMiD, ISIC2019, and NCTCRC datasets demonstrates consistent improvements over state-of-the-art methods, achieving mean FPR95 reductions of 8.45%, 13.02%, and 36.90% respectively. These gains are further supported by comprehensive ablations that validated the contributions of each component. This enables reliable identification of unfamiliar cases for deferral to clinicians, supporting safer AI-assisted diagnosis in real-world workflows. Our code is available at https://github.com/redboxup/MARVEL.