mlsanityData to 14 Oct 2026

WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation

arXiv 2303.14814 ↗First posted 26 Mar 2023cs.CV cs.AI cs.CLcited by 315

Not on the map. Why?

Cited by 54 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Visual anomaly classification and segmentation are vital for automating industrial quality inspection. The focus of prior research in the field has been on training custom models for each quality inspection task, which requires task-specific images and annotation. In this paper we move away from this regime, addressing zero-shot and few-normal-shot anomaly classification and segmentation. Recently CLIP, a vision-language model, has shown revolutionary generality with competitive zero-/few-shot performance in comparison to full-supervision. But CLIP falls short on anomaly classification and segmentation tasks. Hence, we propose window-based CLIP (WinCLIP) with (1) a compositional ensemble on state words and prompt templates and (2) efficient extraction and aggregation of window/patch/image-level features aligned with text. We also propose its few-normal-shot extension WinCLIP+, which uses complementary information from normal images. In MVTec-AD (and VisA), without further tuning, WinCLIP achieves 91.8%/85.1% (78.1%/79.6%) AUROC in zero-shot anomaly classification and segmentation while WinCLIP+ does 93.1%/95.2% (83.8%/96.4%) in 1-normal-shot, surpassing state-of-the-art by large margins.

Key facts. Cited by 315 papers in the map (data through 14 Oct 2026). Builds on 46 of its 60 references that are in the map. First posted on arXiv 26 Mar 2023.

Builds on

46 of 60 references.

References · 46

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  8. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  10. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  11. 2016Wide Residual Networkscited by 3,070
  12. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
34 more
  1. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  2. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  3. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
  4. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  5. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 745
  6. 2020Contrastive Learning of Medical Visual Representations from Paired Images and Textcited by 641
  7. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 616
  8. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  9. 2021Extract Free Dense Labels from CLIPcited by 583
  10. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 532
  11. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  12. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  13. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 454
  14. 2022Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Taskscited by 421
  15. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  16. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  17. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
  18. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  19. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  20. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  21. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  22. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  23. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  24. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  25. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  26. 2022Unified Contrastive Learning in Image-Text-Label Spacecited by 194
  27. 2021ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmeticcited by 150
  28. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  29. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  30. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  31. 2021Open World Compositional Zero-Shot Learningcited by 101
  32. 2022MemSeg: A semi-supervised method for image surface defect detection using differences and commonalitiescited by 68
  33. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  34. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 25; 2024: 70; 2025: 113; 2026: 107.

315 papers.

Sort:

By area:

  1. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  2. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  3. 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
  4. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  5. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  6. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  7. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  8. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  9. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  10. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  11. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  12. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
38 more
  1. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detectioncited by 58
  2. 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
  3. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  4. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  5. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  6. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  7. 2024VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentationcited by 50
  8. 2024ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentationcited by 49
  9. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 48
  10. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 48
  11. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  12. 2023Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Leadcited by 40
  13. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  14. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detectioncited by 39
  15. 2024Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrievalcited by 36
  16. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  17. 2024MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detectioncited by 35
  18. 2024Image Segmentation in Foundation Model Era: A Surveycited by 35
  19. 2025Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detectioncited by 31
  20. 2023S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captionscited by 30
  21. 2025The MVTec AD 2 Dataset: Advanced Scenarios for Unsupervised Anomaly Detectioncited by 30
  22. 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detectioncited by 29
  23. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 29
  24. 2024Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Promptscited by 28
  25. 2024UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detectioncited by 28
  26. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  27. 2024SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningcited by 27
  28. 2024MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objectscited by 26
  29. 2025Towards Training-free Anomaly Detection with Vision and Language Foundation Modelscited by 26
  30. 2024ResAD: A Simple Framework for Class Generalizable Anomaly Detectioncited by 25
  31. 2024Open-World Semantic Segmentation Including Class Similaritycited by 24
  32. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  33. 2023GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detectioncited by 23
  34. 2024Unseen Visual Anomaly Generationcited by 23
  35. 2023Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrievalcited by 22
  36. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  37. 2024AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusioncited by 21
  38. 2025Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detectioncited by 21

50 most cited of 315 All 315 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation
  2. 2024SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detection
  3. 2026InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection
  4. 2026Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline
  5. 2026MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detection
  6. 2025IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning
  7. 2025PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures
  8. 2025ADSeeker: A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and Reasoning