mlsanityData to 14 Oct 2026

CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection

arXiv 2311.00453 ↗First posted 1 Nov 2023cs.CVcited by 58

Not on the map. Why?

Abstract (arXiv)

This paper considers zero-shot Anomaly Detection (AD), performing AD without reference images of the test objects. We propose a framework called CLIP-AD to leverage the zero-shot capabilities of the large vision-language model CLIP. Firstly, we reinterpret the text prompts design from a distributional perspective and propose a Representative Vector Selection (RVS) paradigm to obtain improved text features. Secondly, we note opposite predictions and irrelevant highlights in the direct computation of the anomaly maps. To address these issues, we introduce a Staged Dual-Path model (SDP) that leverages features from various levels and applies architecture and feature surgery. Lastly, delving deeply into the two phenomena, we point out that the image and text features are not aligned in the joint embedding space. Thus, we introduce a fine-tuning strategy by adding linear layers and construct an extended model SDP+, further enhancing the performance. Abundant experiments demonstrate the effectiveness of our approach, e.g., on MVTec-AD, SDP outperforms the SOTA WinCLIP by +4.2/+10.7 in segmentation metrics F1-max/PRO, while SDP+ achieves +8.3/+20.5 improvements.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). Builds on 19 of its 56 references that are in the map. First posted on arXiv 1 Nov 2023.

Builds on

19 of 56 references.

References · 19

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2023Segment Anythingcited by 8,234
  3. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  4. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  5. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  6. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  7. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  8. 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
  9. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  10. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  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. 2023A Closer Look at the Explainability of Contrastive Language-Image Pre-trainingcited by 96
7 more
  1. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  2. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  3. 2022Exploring Visual Interpretability for Contrastive Language-Image Pre-trainingcited by 30
  4. 2022EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithmcited by 27
  5. 2023Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localizationcited by 10
  6. 2023Zero-Shot Anomaly Detection with Pre-trained Segmentation Modelscited by 8
  7. 2023Multi-Scale Memory Comparison for Zero-/Few-Shot Anomaly Detectioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 16; 2025: 25; 2026: 13.

58 papers.

Sort:

By area:

  1. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  2. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  3. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 111
  4. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  5. 2024VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentationcited by 50
  6. 2024ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentationcited by 49
  7. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  8. 2024Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Promptscited by 40
  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. 2023DiAD: A Diffusion-based Framework for Multi-class Anomaly Detectioncited by 33
  12. 2025Token Activation Map to Visually Explain Multimodal LLMscited by 32
38 more
  1. 2025Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detectioncited by 31
  2. 2024Large Language Models for Anomaly and Out-of-Distribution Detection: A Surveycited by 27
  3. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  4. 2023GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detectioncited by 23
  5. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  6. 2024A Survey on Safe Multi-Modal Learning Systemcited by 15
  7. 2026VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformercited by 11
  8. 2024Learning Multi-view Anomaly Detection with Efficient Adaptive Selectioncited by 9
  9. 2025Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Processcited by 8
  10. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  11. 2024Dual-path Frequency Discriminators for Few-shot Anomaly Detectioncited by 7
  12. 2025Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Modelscited by 6
  13. 2026MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrievalcited by 6
  14. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
  15. 2025Out-of-Distribution Detection using Synthetic Data Generationcited by 4
  16. 2025CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognitioncited by 4
  17. 2025Continual-MEGA: A Large-scale Benchmark for Generalizable Continual Anomaly Detectioncited by 4
  18. 2026AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectorscited by 4
  19. 2026GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learningcited by 4
  20. 2024ONER: Online Experience Replay for Incremental Anomaly Detectioncited by 3
  21. 2025Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detectioncited by 3
  22. 2025Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Promptscited by 3
  23. 2026Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Modelscited by 3
  24. 2025PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awarenesscited by 2
  25. 2025StackCLIP: Clustering-Driven Stacked Prompt in Zero-Shot Industrial Anomaly Detectioncited by 2
  26. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  27. 2025IQE-CLIP: Instance-aware Query Embedding for Zero-/Few-shot Anomaly Detection in Medical Domaincited by 1
  28. 2025Zero-Shot Anomaly Detection with Dual-Branch Prompt Selectioncited by 1
  29. 2025CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detectioncited by 1
  30. 2025A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detectioncited by 1
  31. 2026AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Modelscited by 1
  32. 2026WMoE-CLIP: Wavelet-Enhanced Mixture-of-Experts Prompt Learning for Zero-Shot Anomaly Detectioncited by 1
  33. 2026FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglementcited by 1
  34. 2024GlocalCLIP: Object-agnostic Global-Local Prompt Learning for Zero-shot Anomaly Detectioncited by 0
  35. 2024CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIPcited by 0
  36. 2025Zero-Shot Industrial Anomaly Segmentation with Image-Aware Prompt Generationcited by 0
  37. 2025ViP2-CLIP: Visual-Perception Prompting with Unified Alignment for Zero-Shot Anomaly Detectioncited by 0
  38. 2025Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detectioncited by 0

50 most cited of 58 All 58 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection
  2. 2025KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration
  3. 2026TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection
  4. 2025Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and Segmentation
  5. 2024FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model
  6. 2026Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection
  7. 2025PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures
  8. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models