mlsanityData to 7 Oct 2026

A Unified Model for Multi-class Anomaly Detection

arXiv 2206.03687 ↗First posted 8 Jun 2022cs.CVcited by 267

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite the rapid advance of unsupervised anomaly detection, existing methods require to train separate models for different objects. In this work, we present UniAD that accomplishes anomaly detection for multiple classes with a unified framework. Under such a challenging setting, popular reconstruction networks may fall into an "identical shortcut", where both normal and anomalous samples can be well recovered, and hence fail to spot outliers. To tackle this obstacle, we make three improvements. First, we revisit the formulations of fully-connected layer, convolutional layer, as well as attention layer, and confirm the important role of query embedding (i.e., within attention layer) in preventing the network from learning the shortcut. We therefore come up with a layer-wise query decoder to help model the multi-class distribution. Second, we employ a neighbor masked attention module to further avoid the information leak from the input feature to the reconstructed output feature. Third, we propose a feature jittering strategy that urges the model to recover the correct message even with noisy inputs. We evaluate our algorithm on MVTec-AD and CIFAR-10 datasets, where we surpass the state-of-the-art alternatives by a sufficiently large margin. For example, when learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88.1% to 96.5%) and anomaly localization (from 89.5% to 96.8%). Code is available at https://github.com/zhiyuanyou/UniAD.

Key facts. Cited by 267 papers in the map (data through 7 Oct 2026). Builds on 39 of its 72 references that are in the map. First posted on arXiv 8 Jun 2022.

Builds on

39 of 72 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  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. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  10. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  11. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  12. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
27 more
  1. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  2. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  3. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  4. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  5. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  6. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
  7. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  8. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  9. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  10. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  11. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 145
  12. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  13. 2020Explainable Deep One-Class Classificationcited by 126
  14. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  15. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  16. 2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
  17. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  18. 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
  19. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  20. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  21. 2020Backpropagated Gradient Representations for Anomaly Detectioncited by 54
  22. 2020Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Imagescited by 52
  23. 2019Detecting semantic anomaliescited by 50
  24. 2020Iterative energy-based projection on a normal data manifold for anomaly localizationcited by 47
  25. 2020G2D: Generate to Detect Anomalycited by 42
  26. 2020Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noisecited by 39
  27. 2022AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decodercited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 40; 2024: 68; 2025: 89; 2026: 66.

267 papers.

Sort:

By area:

  1. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  2. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  3. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  4. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  5. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  6. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  7. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  8. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  9. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  10. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 72
  11. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  12. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
38 more
  1. 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstructioncited by 62
  2. 2024Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Modelscited by 55
  3. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  4. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  5. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  6. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 47
  7. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  8. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
  9. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detectioncited by 42
  10. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detectioncited by 39
  11. 2024Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detectioncited by 35
  12. 2023DiAD: A Diffusion-based Framework for Multi-class Anomaly Detectioncited by 33
  13. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  14. 2024Unsupervised Continual Anomaly Detection with Contrastively-learned Promptcited by 31
  15. 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detectioncited by 29
  16. 2024Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detectioncited by 28
  17. 2024UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detectioncited by 28
  18. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 28
  19. 2024MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objectscited by 26
  20. 2023An Incremental Unified Framework for Small Defect Inspectioncited by 25
  21. 2024MedIAnomaly: A comparative study of anomaly detection in medical imagescited by 25
  22. 2024ResAD: A Simple Framework for Class Generalizable Anomaly Detectioncited by 24
  23. 2025Towards Training-free Anomaly Detection with Vision and Language Foundation Modelscited by 24
  24. 2023GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detectioncited by 23
  25. 2024Unseen Visual Anomaly Generationcited by 23
  26. 2025MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detectioncited by 23
  27. 2023Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale Reconstructioncited by 22
  28. 2024Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspectivecited by 22
  29. 2024PixOOD: Pixel-Level Out-of-Distribution Detectioncited by 20
  30. 2022MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detectioncited by 19
  31. 2024Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detectioncited by 19
  32. 2024Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detectioncited by 19
  33. 2025One-for-More: Continual Diffusion Model for Anomaly Detectioncited by 19
  34. 2022Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detectioncited by 18
  35. 2025Learning to Detect Multi-class Anomalies with Just One Normal Image Promptcited by 18
  36. 2023Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approachcited by 17
  37. 2024Continuous Memory Representation for Anomaly Detectioncited by 16
  38. 2024Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detectioncited by 16

50 most cited of 267 All 267 (JSON)