mlsanityData to 7 Oct 2026

Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection

arXiv 2503.02424 ↗First posted 4 Mar 2025cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

Anomaly detection (AD) is essential for industrial inspection, yet existing methods typically rely on ``comparing'' test images to normal references from a training set. However, variations in appearance and positioning often complicate the alignment of these references with the test image, limiting detection accuracy. We observe that most anomalies manifest as local variations, meaning that even within anomalous images, valuable normal information remains. We argue that this information is useful and may be more aligned with the anomalies since both the anomalies and the normal information originate from the same image. Therefore, rather than relying on external normality from the training set, we propose INP-Former, a novel method that extracts Intrinsic Normal Prototypes (INPs) directly from the test image. Specifically, we introduce the INP Extractor, which linearly combines normal tokens to represent INPs. We further propose an INP Coherence Loss to ensure INPs can faithfully represent normality for the testing image. These INPs then guide the INP-Guided Decoder to reconstruct only normal tokens, with reconstruction errors serving as anomaly scores. Additionally, we propose a Soft Mining Loss to prioritize hard-to-optimize samples during training. INP-Former achieves state-of-the-art performance in single-class, multi-class, and few-shot AD tasks across MVTec-AD, VisA, and Real-IAD, positioning it as a versatile and universal solution for AD. Remarkably, INP-Former also demonstrates some zero-shot AD capability. Code is available at:https://github.com/luow23/INP-Former.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 40 of its 53 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

40 of 53 references.

References · 40

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2023Vision Transformers Need Registerscited by 844
  6. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  7. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  8. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  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. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  12. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
28 more
  1. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  2. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  3. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  4. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  5. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  6. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  7. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  8. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  9. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 126
  10. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  11. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  12. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 97
  13. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  14. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
  15. 2023Stable and low-precision training for large-scale vision-language modelscited by 74
  16. 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
  17. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  18. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  19. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  20. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  21. 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstructioncited by 62
  22. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 56
  23. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  24. 2021Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localizationcited by 32
  25. 2024Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detectioncited by 28
  26. 2024Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detectioncited by 19
  27. 2024AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localizationcited by 12
  28. 2024VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modelingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 19; 2026: 28.

47 papers.

Sort:

By area:

  1. 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
  2. 2025Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detectioncited by 7
  3. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  4. 2025Dinomaly2: A Unified Framework for Unsupervised Image Anomaly Detectioncited by 6
  5. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  6. 2025Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmarkcited by 3
  7. 2025RoBiS: Robust Binary Segmentation for High-Resolution Industrial Imagescited by 3
  8. 2026Dual Distillation for Few-Shot Anomaly Detectioncited by 3
  9. 2025ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learningcited by 2
  10. 2026AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectorscited by 2
  11. 2025Search is All You Need for Few-shot Anomaly Detectioncited by 1
  12. 2025Leveraging Learning Bias for Noisy Anomaly Detectioncited by 1
35 more
  1. 2025From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challengecited by 1
  2. 2025AnyAD: Unified Any-Modality Anomaly Detection in Incomplete Multi-Sequence MRIcited by 1
  3. 2026MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Modelscited by 1
  4. 2026Memory-Distilled Selection for Noise-Robust Anomaly Detectioncited by 1
  5. 2026Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimizationcited by 1
  6. 2026ProCon: Projection-Consistency Memory for Training-Free Anomaly Detectioncited by 1
  7. 2026IMMoE: Incomplete Multi-View Anomaly Detection via Mixture of View Experts Fusioncited by 1
  8. 2026A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detectioncited by 1
  9. 2025Pro-AD: Learning Comprehensive Prototypes with Prototype-based Constraint for Multi-class Unsupervised Anomaly Detectioncited by 0
  10. 2025Multi-View Reconstruction with Global Context for 3D Anomaly Detectioncited by 0
  11. 2025Self-Navigated Residual Mamba for Universal Industrial Anomaly Detectioncited by 0
  12. 2025Diverse Normal Prototypes-Guided Contrastive Reconstruction for Medical Anomaly Detectioncited by 0
  13. 2025Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localizationcited by 0
  14. 2025Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Datasetcited by 0
  15. 2025ProtoAnomalyNCD: Prototype Learning for Multi-class Novel Anomaly Discovery in Industrial Scenarioscited by 0
  16. 2026HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detectioncited by 0
  17. 2026A Feature Shuffling and Restoration Strategy for Universal Unsupervised Anomaly Detectioncited by 0
  18. 2026PiCo: Active Manifold Canonicalization for Robust Robotic Visual Anomaly Detectioncited by 0
  19. 2026Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detectioncited by 0
  20. 2026Novel Anomaly Detection Scenarios and Evaluation Metrics to Address the Ambiguity in the Definition of Normal Samplescited by 0
  21. 2026GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesiscited by 0
  22. 2026Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detectioncited by 0
  23. 2026SuperADD: Training-free Class-agnostic Anomaly Segmentation -- CVPR 2026 VAND 4.0 Workshop Challenge Industrial Trackcited by 0
  24. 2026Beyond Normal References: Discriminative Few-Shot Anomaly Detectioncited by 0
  25. 2026Dual Prototype-Conditioned Diffusion Model for Scalable Multi-Class Unsupervised Anomaly Detection in Large Category Spacescited by 0
  26. 2026Towards Active Real-to-Twin Inspection: A New Paradigm for Zero-Shot Anomaly Detectioncited by 0
  27. 2026Disentangled Fine-Grained Prototype Learning for Incomplete Image-Tabular Classificationcited by 0
  28. 2026LogiCo: A Unified Framework for Logical and Structural Anomaly Detectioncited by 0
  29. 2026ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturingcited by 0
  30. 2026PADFormer: Pose-agnostic Anomaly Detection from Sparse View Imagescited by 0
  31. 2026GuidedFlow: An Attention-Guided Framework for Anomaly Detection in Additive Manufacturingcited by 0
  32. 2026What Remains Normal? Clean Images Miss Useful Near-Defect Normal Patches for Anomaly Detectioncited by 0
  33. 2026DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generationcited by 0
  34. 2026NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detectioncited by 0
  35. 2026GaugeDefect: Detecting Surface Anomalies by Curvature of Feature Transportcited by 0