mlsanityData to 7 Oct 2026

Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection

arXiv 2405.04782 ↗First posted 8 May 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Image Anomaly Detection has been a challenging task in Computer Vision field. The advent of Vision-Language models, particularly the rise of CLIP-based frameworks, has opened new avenues for zero-shot anomaly detection. Recent studies have explored the use of CLIP by aligning images with normal and prompt descriptions. However, the exclusive dependence on textual guidance often falls short, highlighting the critical importance of additional visual references. In this work, we introduce a Dual-Image Enhanced CLIP approach, leveraging a joint vision-language scoring system. Our methods process pairs of images, utilizing each as a visual reference for the other, thereby enriching the inference process with visual context. This dual-image strategy markedly enhanced both anomaly classification and localization performances. Furthermore, we have strengthened our model with a test-time adaptation module that incorporates synthesized anomalies to refine localization capabilities. Our approach significantly exploits the potential of vision-language joint anomaly detection and demonstrates comparable performance with current SOTA methods across various datasets.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 35 of its 48 references that are in the map. First posted on arXiv 8 May 2024.

Builds on

35 of 48 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  6. 2013Describing Textures in the Wildcited by 2,110
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  8. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  9. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  11. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  12. 2021Extract Free Dense Labels from CLIPcited by 580
23 more
  1. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  2. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  3. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  4. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
  5. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  6. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  7. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  8. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  9. 2020VirTex: Learning Visual Representations from Textual Annotationscited by 338
  10. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  11. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  12. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  13. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  14. 2023Self-regulating Prompts: Foundational Model Adaptation without Forgettingcited by 272
  15. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  16. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  17. 2022F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Modelscited by 149
  18. 2019Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detectioncited by 100
  19. 2023A Closer Look at the Explainability of Contrastive Language-Image Pre-trainingcited by 95
  20. 2022Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Studycited by 66
  21. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  22. 2023Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detectioncited by 15
  23. 2024Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localizationcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
  2. 2024Context-Aware Multimodal Pretrainingcited by 3
  3. 2025TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detectioncited by 1
  4. 2025Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
  2. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection
  3. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection
  4. 2026TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection
  5. 2024Anomaly Detection by Adapting a pre-trained Vision Language Model
  6. 2026FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement
  7. 2024Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection
  8. 2024VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation