mlsanityData to 7 Oct 2026

FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement

arXiv 2603.19608 ↗First posted 20 Mar 2026cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Fine-grained anomaly detection is crucial in industrial and medical applications, but labeled anomalies are often scarce, making zero-shot detection challenging. While vision-language models like CLIP offer promising solutions, they struggle with foreground-background feature entanglement and coarse textual semantics. We propose FB-CLIP, a framework that enhances anomaly localization via multi-strategy textual representations and foreground-background separation. In the textual modality, it combines End-of-Text features, global-pooled representations, and attention-weighted token features for richer semantic cues. In the visual modality, multi-view soft separation along identity, semantic, and spatial dimensions, together with background suppression, reduces interference and improves discriminability. Semantic Consistency Regularization (SCR) aligns image features with normal and abnormal textual prototypes, suppressing uncertain matches and enlarging semantic gaps. Experiments show that FB-CLIP effectively distinguishes anomalies from complex backgrounds, achieving accurate fine-grained anomaly detection and localization under zero-shot settings.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 48 of its 67 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

48 of 67 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  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. 2023Segment Anythingcited by 8,158
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  6. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  7. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  8. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  9. 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 588
  10. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  11. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  12. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 333
36 more
  1. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  2. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  3. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  4. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  5. 2023CLIP-Driven Universal Model for Organ Segmentation and Tumor Detectioncited by 224
  6. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
  7. 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 197
  8. 2021Visual Saliency Transformercited by 175
  9. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  10. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  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 128
  12. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  13. 2020Explainable Deep One-Class Classificationcited by 126
  14. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 126
  15. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  16. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 97
  17. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 87
  18. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  19. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  20. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 72
  21. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  22. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  23. 2022Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Studycited by 66
  24. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detectioncited by 58
  25. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  26. 2022HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformerscited by 46
  27. 2021Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Imagescited by 45
  28. 2023Anomaly Detection under Distribution Shiftcited by 35
  29. 2025Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detectioncited by 31
  30. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 28
  31. 2022ViT-CX: Causal Explanation of Vision Transformerscited by 27
  32. 2021Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Imagescited by 23
  33. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  34. 2023RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detectioncited by 12
  35. 2025AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptationcited by 7
  36. 2026DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection
  2. 2024Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection
  3. 2026VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer
  4. 2026AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
  5. 2025Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection
  6. 2024VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation
  7. 2026TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection
  8. 2026NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection