mlsanityData to 14 Oct 2026

Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detection

arXiv 2406.11507 ↗First posted 17 Jun 2024cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Image anomaly detection plays a pivotal role in industrial inspection. Traditional approaches often demand distinct models for specific categories, resulting in substantial deployment costs. This raises concerns about multi-class anomaly detection, where a unified model is developed for multiple classes. However, applying conventional methods, particularly reconstruction-based models, directly to multi-class scenarios encounters challenges such as identical shortcut learning, hindering effective discrimination between normal and abnormal instances. To tackle this issue, our study introduces the Prior Normality Prompt Transformer (PNPT) method for multi-class image anomaly detection. PNPT strategically incorporates normal semantics prompting to mitigate the "identical mapping" problem. This entails integrating a prior normality prompt into the reconstruction process, yielding a dual-stream model. This innovative architecture combines normal prior semantics with abnormal samples, enabling dual-stream reconstruction grounded in both prior knowledge and intrinsic sample characteristics. PNPT comprises four essential modules: Class-Specific Normality Prompting Pool (CS-NPP), Hierarchical Patch Embedding (HPE), Semantic Alignment Coupling Encoding (SACE), and Contextual Semantic Conditional Decoding (CSCD). Experimental validation on diverse benchmark datasets and real-world industrial applications highlights PNPT's superior performance in multi-class industrial anomaly detection.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 20 of its 30 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

20 of 30 references.

References · 20

  1. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  2. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  3. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  4. 2021Image Segmentation Using Text and Image Promptscited by 512
  5. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  6. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  7. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  8. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  9. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  10. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  11. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  12. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
8 more
  1. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  2. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 80
  3. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 57
  4. 2022TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformercited by 42
  5. 2022Self-Supervised Masked Convolutional Transformer Block for Anomaly Detectioncited by 34
  6. 2023DiAD: A Diffusion-based Framework for Multi-class Anomaly Detectioncited by 33
  7. 2023Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detectioncited by 21
  8. 2023A Discrepancy Aware Framework for Robust Anomaly Detectioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 12; 2026: 5.

19 papers.

Sort:

By area:

  1. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 48
  2. 2026VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformercited by 11
  3. 2024VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modelingcited by 9
  4. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  5. 2025Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detectioncited by 7
  6. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  7. 2025A VLM-based Method for Visual Anomaly Detection in Robotic Scientific Laboratoriescited by 5
  8. 2025Exploring Few-Shot Defect Segmentation in General Industrial Scenarios with Metric Learning and Vision Foundation Modelscited by 4
  9. 2026Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectivecited by 4
  10. 2025GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detectioncited by 3
  11. 2025MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samplescited by 3
  12. 2026A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detectioncited by 3
7 more
  1. 2024View-Invariant Pixelwise Anomaly Detection in Multi-object Scenes with Adaptive View Synthesiscited by 2
  2. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  3. 2025CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detectioncited by 1
  4. 2026Multi-AD: Cross-Domain Unsupervised Anomaly Detection for Medical and Industrial Applicationscited by 1
  5. 2026URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detectioncited by 1
  6. 2025Domain Adaptation of Attention Heads for Zero-shot Anomaly Detectioncited by 0
  7. 2025Collaborative Reconstruction and Repair for Multi-class Industrial Anomaly Detectioncited by 0