mlsanityData to 14 Oct 2026

MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors

arXiv 2605.05891 ↗First posted 7 May 2026cs.CV cs.AI cs.LGcited by 0

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

Anomaly detection in medical images is a challenging task, since anomalies are not typically available during training. Recent methods leverage a single pretext task coupled with a large-scale pre-trained model to reach state-of-the-art performance. Instead, we propose to learn multiple self-supervised and pseudo-labeling tasks from scratch, using a joint model based on Mixture-of-Experts (MoE). By carefully integrating multiple proxy tasks, the joint model effectively learns a robust representation of normal anatomical structures, so that anomaly scores can be derived based on how well the multi-task learner (MTL) solves each task during inference. We perform comprehensive experiments on BMAD, a recent benchmark that comprises a broad range of medical image modalities. The empirical results indicate that our multi-task learner is an effective anomaly detector, outperforming all state-of-the-art competitors on BMAD. Moreover, our model produces interpretable anomaly maps, potentially helping physicians in providing more accurate diagnoses.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 62 of its 79 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

62 of 79 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design26 Oct

Other references · 61

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  7. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  8. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  9. 2025Qwen-Image Technical Reportcited by 1,044
  10. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  11. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  12. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
38 more
  1. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  2. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  3. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  4. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  5. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  6. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
  7. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  8. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  9. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  10. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  11. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  12. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  13. 2021Curriculum Learning: A Surveycited by 259
  14. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  15. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  16. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  17. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  18. 2022Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Modelscited by 97
  19. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  20. 2018Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoderscited by 83
  21. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 82
  22. 2023FAMO: Fast Adaptive Multitask Optimizationcited by 78
  23. 2019Unsupervised Anomaly Localization using Variational Auto-Encoderscited by 73
  24. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  25. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  26. 2022Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzlescited by 62
  27. 2019Multimodal Self-Supervised Learning for Medical Image Analysiscited by 57
  28. 2022Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learnerscited by 51
  29. 2022SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detectioncited by 45
  30. 2023Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRIcited by 45
  31. 2020Detecting Outliers with Foreign Patch Interpolationcited by 44
  32. 2024MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detectioncited by 35
  33. 2024Masked Image Modeling: A Surveycited by 29
  34. 2024UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detectioncited by 28
  35. 2024MedIAnomaly: A comparative study of anomaly detection in medical imagescited by 26
  36. 2021Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Imagescited by 23
  37. 2023The role of noise in denoising models for anomaly detection in medical imagescited by 23
  38. 2024Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspectivecited by 23

50 most cited of 61 All 61 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Images
  2. 2026Dual Distillation for Few-Shot Anomaly Detection
  3. 2026PDD: Manifold-Prior Diverse Distillation for Medical Anomaly Detection
  4. 2026MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence
  5. 2026Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learning
  6. 2025SP-Mamba: Spatial-Perception State Space Model for Unsupervised Medical Anomaly Detection
  7. 2026Multi-AD: Cross-Domain Unsupervised Anomaly Detection for Medical and Industrial Applications
  8. 2026MedAD-R1: Eliciting Consistent Reasoning in Interpretible Medical Anomaly Detection via Consistency-Reinforced Policy Optimization