mlsanityData to 14 Oct 2026

PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection

arXiv 2404.05231 ↗First posted 8 Apr 2024cs.CVcited by 98

Not on the map. Why?

Abstract (arXiv)

The vision-language model has brought great improvement to few-shot industrial anomaly detection, which usually needs to design of hundreds of prompts through prompt engineering. For automated scenarios, we first use conventional prompt learning with many-class paradigm as the baseline to automatically learn prompts but found that it can not work well in one-class anomaly detection. To address the above problem, this paper proposes a one-class prompt learning method for few-shot anomaly detection, termed PromptAD. First, we propose semantic concatenation which can transpose normal prompts into anomaly prompts by concatenating normal prompts with anomaly suffixes, thus constructing a large number of negative samples used to guide prompt learning in one-class setting. Furthermore, to mitigate the training challenge caused by the absence of anomaly images, we introduce the concept of explicit anomaly margin, which is used to explicitly control the margin between normal prompt features and anomaly prompt features through a hyper-parameter. For image-level/pixel-level anomaly detection, PromptAD achieves first place in 11/12 few-shot settings on MVTec and VisA.

Key facts. Cited by 98 papers in the map (data through 14 Oct 2026). Builds on 44 of its 61 references that are in the map. First posted on arXiv 8 Apr 2024.

Builds on

44 of 61 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  7. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  8. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  9. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  10. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  11. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  12. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
32 more
  1. 2019How Can We Know What Language Models Know?cited by 959
  2. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  3. 2022MaPLe: Multi-modal Prompt Learningcited by 687
  4. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  5. 2021Extract Free Dense Labels from CLIPcited by 583
  6. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  7. 2021VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Expertscited by 425
  8. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  9. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  10. 2021CRIS: CLIP-Driven Referring Image Segmentationcited by 353
  11. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  12. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  13. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  14. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  15. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  16. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  17. 2022CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labelscited by 181
  18. 2022ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentationcited by 178
  19. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 160
  20. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  21. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 146
  22. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  23. 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
  24. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  25. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  26. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  27. 2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
  28. 2022Exploring Visual Interpretability for Contrastive Language-Image Pre-trainingcited by 30
  29. 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
  30. 2022Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimationcited by 24
  31. 2023Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detectioncited by 16
  32. 2023Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignmentcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 14; 2025: 49; 2026: 35.

98 papers.

Sort:

By area:

  1. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  2. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 48
  3. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  4. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 29
  5. 2024MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objectscited by 26
  6. 2025Towards Training-free Anomaly Detection with Vision and Language Foundation Modelscited by 26
  7. 2024Unseen Visual Anomaly Generationcited by 23
  8. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  9. 2025One-for-More: Continual Diffusion Model for Anomaly Detectioncited by 19
  10. 2024Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detectioncited by 15
  11. 2024SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detectioncited by 14
  12. 2025MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learningcited by 13
38 more
  1. 2025MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learningcited by 12
  2. 2025Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detectioncited by 12
  3. 2026VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformercited by 11
  4. 2025Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detectioncited by 10
  5. 2025DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookupcited by 10
  6. 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
  7. 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detectioncited by 8
  8. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  9. 2024FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Modelcited by 7
  10. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  11. 2025FastRef:Fast Prototype Refinement for Few-Shot Industrial Anomaly Detectioncited by 7
  12. 2025AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptationcited by 7
  13. 2025Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptationcited by 7
  14. 2026SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modelingcited by 7
  15. 2025Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memorycited by 6
  16. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
  17. 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparisoncited by 5
  18. 2024PIG: Prompt Images Guidance for Night-Time Scene Parsingcited by 4
  19. 2024Bidirectional Multimodal Prompt Learning with Scale-Aware Training for Few-Shot Multi-Class Anomaly Detectioncited by 4
  20. 2025Continual-MEGA: A Large-scale Benchmark for Generalizable Continual Anomaly Detectioncited by 4
  21. 2025Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detectioncited by 4
  22. 2025AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentationcited by 4
  23. 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detectioncited by 4
  24. 2026AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectorscited by 4
  25. 2026Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectivecited by 4
  26. 2025Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detectioncited by 3
  27. 2025GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detectioncited by 3
  28. 2025MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samplescited by 3
  29. 2024Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Schemecited by 2
  30. 2024SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detectioncited by 2
  31. 2025PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awarenesscited by 2
  32. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  33. 2025Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detectioncited by 2
  34. 2025PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixturescited by 2
  35. 2025ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categoriescited by 2
  36. 2026GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detectioncited by 2
  37. 2026Is Task-Specific Training Necessary for Anomaly Detection?cited by 2
  38. 2026EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Modelscited by 2

50 most cited of 98 All 98 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and Segmentation
  2. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection
  3. 2024Anomaly Detection by Adapting a pre-trained Vision Language Model
  4. 2026SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection
  5. 2025CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
  6. 2026TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection
  7. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts
  8. 2026CORE: Contrast-and-Reflect for Self-Supervised Prompt Optimization in Anomaly Synthesis