mlsanityData to 7 Oct 2026

Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging

arXiv 2605.05161 ↗First posted 6 May 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Zero-shot anomaly localisation via vision-language models (VLMs) offers a compelling approach for rare pathology detection, yet its performance is fundamentally limited by the absence of healthy anatomical context. We reformulate zero-shot localisation as a comparative inference problem in which anomalies are identified through structured comparison against reference distributions of normal anatomy. We introduce WALDO, a training-free framework grounded in optimal transport theory that enables comparative reasoning through: (i) entropy-weighted Sliced Wasserstein distances for anatomically-aware reference selection from DINOv2 patch distributions, (ii) Goldilocks zone sampling exploiting the non-monotonic relationship between reference similarity and localisation accuracy, and (iii) self-consistency aggregation via weighted non-maximum suppression. We theoretically analyse the Goldilocks effect through distributional divergence, and show that references with moderate similarity minimize a bias-variance trade-off in comparative visual reasoning. On the NOVA brain MRI benchmark, WALDO with Qwen2.5-VL-72B achieves 43.5±1.6% mAP@30 (95% CI: [40.4, 46.7]), representing a 19% relative improvement over zero-shot baselines. Cross-model evaluation shows consistent gains: GPT-4o achieves 32.0±6.5% and Qwen3-VL-32B achieves 32.0±6.6% mAP@30. Paired McNemar tests confirm statistical significance (p<0.01). Source code is available at https://github.com/bkainz/WALDOMICCAI26demo .

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 19 of its 33 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

19 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in Brain MRI20 May

Other references · 18

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2024GPT-4o System Cardcited by 4,467
  7. 2025Qwen3-VL Technical Reportcited by 2,534
  8. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  9. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  10. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  11. 2015Optimal Transport for Domain Adaptationcited by 457
  12. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
6 more
  1. 2020VinDr-CXR: An open dataset of chest X-rays with radiologist's annotationscited by 236
  2. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  3. 2020Detecting Outliers with Foreign Patch Interpolationcited by 44
  4. 2023Many tasks make light work: Learning to localise medical anomalies from multiple synthetic taskscited by 12
  5. 2024Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detectioncited by 12
  6. 2022nnOOD: A Framework for Benchmarking Self-supervised Anomaly Localisation Methodscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Layer Selection in VLMs for Zero-Shot OOD Detection via Multi-Resolution Entropy Estimation
  2. 2025Delving into Out-of-Distribution Detection with Medical Vision-Language Models
  3. 2026Training-Free Zero-Shot Anomaly Detection in 3D Brain MRI with 2D Foundation Models
  4. 2026PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs
  5. 2026Training Free Zero-Shot Visual Anomaly Localization via Diffusion Inversion
  6. 2026GAZE: Grounded Agentic Zero-shot Evaluation with Viewer-Level Tools and Literature Retrieval on Rare Brain MRI
  7. 2026Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images
  8. 2025On the Problem of Consistent Anomalies in Zero-Shot Anomaly Detection