mlsanityData to 7 Oct 2026

Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization

arXiv 2308.15939 ↗First posted 30 Aug 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Contrastive Language-Image Pre-training (CLIP) models have shown promising performance on zero-shot visual recognition tasks by learning visual representations under natural language supervision. Recent studies attempt the use of CLIP to tackle zero-shot anomaly detection by matching images with normal and abnormal state prompts. However, since CLIP focuses on building correspondence between paired text prompts and global image-level representations, the lack of fine-grained patch-level vision to text alignment limits its capability on precise visual anomaly localization. In this work, we propose AnoCLIP for zero-shot anomaly localization. In the visual encoder, we introduce a training-free value-wise attention mechanism to extract intrinsic local tokens of CLIP for patch-level local description. From the perspective of text supervision, we particularly design a unified domain-aware contrastive state prompting template for fine-grained vision-language matching. On top of the proposed AnoCLIP, we further introduce a test-time adaptation (TTA) mechanism to refine visual anomaly localization results, where we optimize a lightweight adapter in the visual encoder using AnoCLIP's pseudo-labels and noise-corrupted tokens. With both AnoCLIP and TTA, we significantly exploit the potential of CLIP for zero-shot anomaly localization and demonstrate the effectiveness of AnoCLIP on various datasets.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 46 of its 55 references that are in the map. First posted on arXiv 30 Aug 2023.

Builds on

46 of 55 references.

References · 46

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2016Wide Residual Networkscited by 3,057
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  9. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  10. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  11. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  12. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
34 more
  1. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  2. 2021Robust fine-tuning of zero-shot modelscited by 785
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  4. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  5. 2021Extract Free Dense Labels from CLIPcited by 580
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  8. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
  9. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  10. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  11. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  12. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  13. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  14. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  15. 2020VirTex: Learning Visual Representations from Textual Annotationscited by 338
  16. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  17. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  18. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  19. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  20. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  21. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  22. 2020Universal Source-Free Domain Adaptationcited by 219
  23. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  24. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  25. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  26. 2015Learning Visual Features from Large Weakly Supervised Datacited by 165
  27. 2022F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Modelscited by 149
  28. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  29. 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 128
  30. 2020Explainable Deep One-Class Classificationcited by 126
  31. 2022ReCo: Retrieve and Co-segment for Zero-shot Transfercited by 115
  32. 2023A Closer Look at the Explainability of Contrastive Language-Image Pre-trainingcited by 95
  33. 2022MAEDAY: MAE for few and zero shot AnomalY-Detectioncited by 30
  34. 2021Out-of-Distribution Detection Without Class Labelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 6; 2026: 2.

10 papers.

  1. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detectioncited by 58
  2. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detectioncited by 39
  3. 2025IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detectioncited by 17
  4. 2025FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localizationcited by 7
  5. 2025The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Modelscited by 7
  6. 2025Out-of-Distribution Detection using Synthetic Data Generationcited by 4
  7. 2025Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detectioncited by 0
  8. 2025Anomalous Decision Discovery using Inverse Reinforcement Learningcited by 0
  9. 2026GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Modelscited by 0
  10. 2026Dual Anchors, Do It Better: Hierarchical Group Merging for Zero-Shot Anomaly Detectioncited by 0