mlsanityData to 14 Oct 2026

MadCLIP: Few-shot Medical Anomaly Detection with CLIP

arXiv 2506.23810 ↗First posted 30 Jun 2025cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

An innovative few-shot anomaly detection approach is presented, leveraging the pre-trained CLIP model for medical data, and adapting it for both image-level anomaly classification (AC) and pixel-level anomaly segmentation (AS). A dual-branch design is proposed to separately capture normal and abnormal features through learnable adapters in the CLIP vision encoder. To improve semantic alignment, learnable text prompts are employed to link visual features. Furthermore, SigLIP loss is applied to effectively handle the many-to-one relationship between images and unpaired text prompts, showcasing its adaptation in the medical field for the first time. Our approach is validated on multiple modalities, demonstrating superior performance over existing methods for AC and AS, in both same-dataset and cross-dataset evaluations. Unlike prior work, it does not rely on synthetic data or memory banks, and an ablation study confirms the contribution of each component. The code is available at https://github.com/mahshid1998/MadCLIP.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

24 of 37 references.

References · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  3. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  4. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  5. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  6. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  7. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  8. 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 570
  9. 2021The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classificationcited by 518
  10. 2019The Liver Tumor Segmentation Benchmark (LiTS)cited by 509
  11. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  12. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
12 more
  1. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  2. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  3. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  4. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  5. 2023APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot ADcited by 130
  6. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  7. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  8. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  9. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  10. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  11. 2024MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detectioncited by 35
  12. 2023OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methodscited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 9.

10 papers.

  1. 2025Diffusion-Based Data Augmentation for Medical Image Segmentationcited by 3
  2. 2026Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Modelscited by 3
  3. 2026HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detectioncited by 1
  4. 2026MedSAD-CLIP: Supervised CLIP with Token-Patch Cross-Attention for Medical Anomaly Detection and Segmentationcited by 0
  5. 2026HAC: Parameter-Efficient Hyperbolic Adaptation of CLIP for Zero-Shot VQAcited by 0
  6. 2026MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectorscited by 0
  7. 2026LADBench: A Benchmark for Logical Fault Detection in Imagescited by 0
  8. 2026DBT-Bleed: Dual-Branch Temporal Modeling with Key-Frame Selection for Surgical Bleeding Detectioncited by 0
  9. 2026Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detectioncited by 0
  10. 2026Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Imagescited by 0