mlsanityData to 14 Oct 2026

AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection

arXiv 2407.15795 ↗First posted 22 Jul 2024cs.CVcited by 127

Not on the map. Why?

Cited by 26 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Zero-shot anomaly detection (ZSAD) targets the identification of anomalies within images from arbitrary novel categories. This study introduces AdaCLIP for the ZSAD task, leveraging a pre-trained vision-language model (VLM), CLIP. AdaCLIP incorporates learnable prompts into CLIP and optimizes them through training on auxiliary annotated anomaly detection data. Two types of learnable prompts are proposed: static and dynamic. Static prompts are shared across all images, serving to preliminarily adapt CLIP for ZSAD. In contrast, dynamic prompts are generated for each test image, providing CLIP with dynamic adaptation capabilities. The combination of static and dynamic prompts is referred to as hybrid prompts, and yields enhanced ZSAD performance. Extensive experiments conducted across 14 real-world anomaly detection datasets from industrial and medical domains indicate that AdaCLIP outperforms other ZSAD methods and can generalize better to different categories and even domains. Finally, our analysis highlights the importance of diverse auxiliary data and optimized prompts for enhanced generalization capacity. Code is available at https://github.com/caoyunkang/AdaCLIP.

Key facts. Cited by 127 papers in the map (data through 14 Oct 2026). Builds on 38 of its 57 references that are in the map. First posted on arXiv 22 Jul 2024.

Builds on

38 of 57 references.

References · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  5. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  6. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  7. 2022Visual Prompt Tuningcited by 1,681
  8. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  9. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  11. 2022MaPLe: Multi-modal Prompt Learningcited by 687
  12. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
26 more
  1. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  2. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  3. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  4. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  5. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  6. 2016Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)cited by 198
  7. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  8. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  9. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  10. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  11. 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
  12. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  13. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 90
  14. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  15. 2021Deep Learning for Chest X-ray Analysis: A Surveycited by 84
  16. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  17. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 68
  18. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  19. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detectioncited by 58
  20. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 57
  21. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  22. 2023DiAD: A Diffusion-based Framework for Multi-class Anomaly Detectioncited by 33
  23. 2022A Feature Memory Rearrangement Network for Visual Inspection of Textured Surface Defects Toward Edge Intelligent Manufacturingcited by 16
  24. 2023Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detectioncited by 16
  25. 2023A Discrepancy Aware Framework for Robust Anomaly Detectioncited by 9
  26. 2022Deep Autoencoders for Anomaly Detection in Textured Images using CW-SSIMcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 69; 2026: 52.

127 papers.

Sort:

By area:

  1. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  2. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  3. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 48
  4. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  5. 2025Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detectioncited by 31
  6. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 29
  7. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  8. 2024Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Frameworkcited by 15
  9. 2025Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defectscited by 15
  10. 2025MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learningcited by 12
  11. 2026VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformercited by 11
  12. 2025DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookupcited by 10
38 more
  1. 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
  2. 2025Taming Vision-Language Models for Medical Image Analysis: A Comprehensive Reviewcited by 9
  3. 2025Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Processcited by 8
  4. 2025Track Any Anomalous Object: A Granular Video Anomaly Detection Pipelinecited by 8
  5. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  6. 2026No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detectioncited by 8
  7. 2025Deep learning based infrared small object segmentation: Challenges and future directionscited by 7
  8. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  9. 2025AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptationcited by 7
  10. 2026SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modelingcited by 7
  11. 2026MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrievalcited by 6
  12. 2024RAD: A Dataset and Benchmark for Real-Life Anomaly Detection with Robotic Observationscited by 5
  13. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
  14. 2025AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesiscited by 5
  15. 2025UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptationcited by 5
  16. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  17. 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparisoncited by 5
  18. 2025Exploiting Point-Language Models with Dual-Prompts for 3D Anomaly Detectioncited by 4
  19. 2025Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detectioncited by 4
  20. 2025Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmarkcited by 4
  21. 2025Continual-MEGA: A Large-scale Benchmark for Generalizable Continual Anomaly Detectioncited by 4
  22. 2025Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detectioncited by 4
  23. 2025Towards Personalized Quantum Federated Learning for Anomaly Detectioncited by 4
  24. 2025AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentationcited by 4
  25. 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detectioncited by 4
  26. 2026AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectorscited by 4
  27. 2026GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learningcited by 4
  28. 2025Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detectioncited by 3
  29. 2025GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detectioncited by 3
  30. 2025VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusioncited by 3
  31. 2025MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samplescited by 3
  32. 2026Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Modelscited by 3
  33. 2024Exploring Zero-Shot Anomaly Detection with CLIP in Medical Imaging: Are We There Yet?cited by 2
  34. 2025PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awarenesscited by 2
  35. 2025VTD-CLIP: Video-to-Text Discretization via Prompting CLIPcited by 2
  36. 2025StackCLIP: Clustering-Driven Stacked Prompt in Zero-Shot Industrial Anomaly Detectioncited by 2
  37. 2025MADPOT: Medical Anomaly Detection with CLIP Adaptation and Partial Optimal Transportcited by 2
  38. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2

50 most cited of 127 All 127 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration
  2. 2024Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection
  3. 2024Anomaly Detection by Adapting a pre-trained Vision Language Model
  4. 2024VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation
  5. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
  6. 2024FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model
  7. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
  8. 2026Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation