mlsanityData to 14 Oct 2026

AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection

arXiv 2310.18961 ↗First posted 29 Oct 2023cs.CVcited by 271

Not on the map. Why?

Cited by 56 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is a crucial task when training data is not accessible due to various concerns, eg, data privacy, yet it is challenging since the models need to generalize to anomalies across different domains where the appearance of foreground objects, abnormal regions, and background features, such as defects/tumors on different products/organs, can vary significantly. Recently large pre-trained vision-language models (VLMs), such as CLIP, have demonstrated strong zero-shot recognition ability in various vision tasks, including anomaly detection. However, their ZSAD performance is weak since the VLMs focus more on modeling the class semantics of the foreground objects rather than the abnormality/normality in the images. In this paper we introduce a novel approach, namely AnomalyCLIP, to adapt CLIP for accurate ZSAD across different domains. The key insight of AnomalyCLIP is to learn object-agnostic text prompts that capture generic normality and abnormality in an image regardless of its foreground objects. This allows our model to focus on the abnormal image regions rather than the object semantics, enabling generalized normality and abnormality recognition on diverse types of objects. Large-scale experiments on 17 real-world anomaly detection datasets show that AnomalyCLIP achieves superior zero-shot performance of detecting and segmenting anomalies in datasets of highly diverse class semantics from various defect inspection and medical imaging domains. Code will be made available at https://github.com/zqhang/AnomalyCLIP.

Key facts. Cited by 271 papers in the map (data through 14 Oct 2026). Builds on 46 of its 62 references that are in the map. First posted on arXiv 29 Oct 2023.

Builds on

46 of 62 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023Segment Anythingcited by 8,234
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  6. 2022Visual Prompt Tuningcited by 1,681
  7. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  8. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  9. 2022MaPLe: Multi-modal Prompt Learningcited by 687
  10. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 616
  11. 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 589
  12. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 532
34 more
  1. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  2. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  3. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  4. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  5. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  6. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  7. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  8. 2023CLIP-Driven Universal Model for Organ Segmentation and Tumor Detectioncited by 224
  9. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  10. 2020Can AI help in screening Viral and COVID-19 pneumonia?cited by 200
  11. 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
  12. 2019Dice Loss for Data-imbalanced NLP Taskscited by 182
  13. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 152
  14. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  15. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  16. 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
  17. 2020Explainable Deep One-Class Classificationcited by 127
  18. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  19. 2023Aligning Bag of Regions for Open-Vocabulary Object Detectioncited by 119
  20. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  21. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  22. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  23. 2023CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Notcited by 79
  24. 2019Attention Based Glaucoma Detection: A Large-scale Database and CNN Modelcited by 76
  25. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  26. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  27. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  28. 2022Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Studycited by 66
  29. 2021Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Imagescited by 45
  30. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  31. 2023Anomaly Detection under Distribution Shiftcited by 35
  32. 2021Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Imagescited by 23
  33. 2023ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Promptscited by 16
  34. 2023RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detectioncited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 55; 2025: 118; 2026: 91.

271 papers.

Sort:

By area:

  1. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  2. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  3. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  4. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  5. 2024FairCLIP: Harnessing Fairness in Vision-Language Learningcited by 69
  6. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detectioncited by 58
  7. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  8. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  9. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  10. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  11. 2024VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentationcited by 50
  12. 2024ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentationcited by 49
38 more
  1. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detectioncited by 47
  2. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  3. 2023Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Leadcited by 40
  4. 2023CLIP in Medical Imaging: A Surveycited by 40
  5. 2024Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Promptscited by 40
  6. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  7. 2025Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detectorcited by 40
  8. 2024Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detectioncited by 36
  9. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  10. 2024MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detectioncited by 35
  11. 2025Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detectioncited by 31
  12. 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detectioncited by 29
  13. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 29
  14. 2024Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Promptscited by 28
  15. 2025AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detectioncited by 28
  16. 2024Large Language Models for Anomaly and Out-of-Distribution Detection: A Surveycited by 27
  17. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  18. 2024SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningcited by 27
  19. 2025Towards Training-free Anomaly Detection with Vision and Language Foundation Modelscited by 26
  20. 2025LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extractioncited by 25
  21. 2023GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detectioncited by 23
  22. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  23. 2025Prompt-based Adaptation in Large-scale Vision Models: A Surveycited by 21
  24. 2025Learning to Detect Multi-class Anomalies with Just One Normal Image Promptcited by 18
  25. 2025OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoningcited by 18
  26. 2026Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysiscited by 18
  27. 2025Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?cited by 17
  28. 2025IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detectioncited by 17
  29. 2023Simple Image-level Classification Improves Open-vocabulary Object Detectioncited by 15
  30. 2024A Survey on Safe Multi-Modal Learning Systemcited by 15
  31. 2023Label-Free Multivariate Time Series Anomaly Detectioncited by 14
  32. 2024IPO: Interpretable Prompt Optimization for Vision-Language Modelscited by 14
  33. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detectioncited by 13
  34. 2025MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learningcited by 13
  35. 2024Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuningcited by 12
  36. 2025MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learningcited by 12
  37. 2025Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detectioncited by 12
  38. 2025EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPOcited by 12

50 most cited of 271 All 271 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
  2. 2026DevPrompt: Deviation-Based Prompt Learning for One-Normal ShotImage Anomaly Detection
  3. 2026Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation
  4. 2025Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation
  5. 2023Efficient Feature Distillation for Zero-shot Annotation Object Detection
  6. 2023Zero-Shot Visual Classification with Guided Cropping
  7. 2025VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection
  8. 2024Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure