mlsanityData to 14 Oct 2026

Beyond Normal References: Discriminative Few-Shot Anomaly Detection

arXiv 2605.23231 ↗First posted 22 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper considers a practical few-shot anomaly detection (FSAD) setting, termed discriminative FSAD, where a limited number of both normal and anomalous examples are available as references during inference. Existing FSAD methods rely on normal-only references through normality matching, ignoring the discriminative clues in anomalous references, while directly fitting both references can overfit to the seen anomalies. We introduce IDEAL, an intrinsic deviation learning framework that leverages both reference types to learn intrinsic deviation patterns characterizing generalizable abnormality as deviations from normality. IDEAL decomposes the learning process into two novel components: 1) a Normal Variation Eraser to suppress nuisance normal variations that may lead to noisy deviations from normality, thereby highlighting anomaly-relevant deviation representations; 2) an Intrinsic Deviation Encoder to decompose these denoised deviation representations into intrinsic deviation vectors capturing the most discriminative orthogonal deviation directions. At inference, IDEAL scores query-to-normal deviations preserved after projection onto the learned intrinsic deviation vectors, enabling generalization for both seen and unseen anomalies. Extensive experiments on eight real-world datasets show that IDEAL generalizes effectively to unseen anomalies and consistently outperforms existing state-of-the-art FSAD methods. Code and data are available at hrefhttps://github.com/mala-lab/IDEALhttps://github.com/mala-lab/IDEAL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 62 of its 92 references that are in the map. First posted on arXiv 22 May 2026.

Builds on

62 of 92 references.

References · 62

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  4. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  5. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  8. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  9. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  10. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  11. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  12. 2019Deep Learning for Anomaly Detection: A Surveycited by 358
38 more
  1. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  2. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  3. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  4. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  5. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  6. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  7. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  8. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  9. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  10. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  11. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  12. 2020Classification-Based Anomaly Detection for General Datacited by 211
  13. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  14. 2019Deep Anomaly Detection with Deviation Networkscited by 153
  15. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  16. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  17. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  18. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  19. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  20. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  21. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  22. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  23. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 82
  24. 2018Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detectioncited by 79
  25. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  26. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  27. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  28. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  29. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  30. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  31. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  32. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  33. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  34. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  35. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 48
  36. 2020Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practicecited by 43
  37. 2023Diversity-Measurable Anomaly Detectioncited by 41
  38. 2023Anomaly Detection under Distribution Shiftcited by 35

50 most cited of 62 All 62 (JSON)

Built on by

Not cited yet.