mlsanityData to 14 Oct 2026

Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection

arXiv 2405.14325 ↗First posted 23 May 2024cs.CVcited by 93

Not on the map. Why?

Abstract (arXiv)

Recent studies highlighted a practical setting of unsupervised anomaly detection (UAD) that builds a unified model for multi-class images. Despite various advancements addressing this challenging task, the detection performance under the multi-class setting still lags far behind state-of-the-art class-separated models. Our research aims to bridge this substantial performance gap. In this paper, we introduce a minimalistic reconstruction-based anomaly detection framework, namely Dinomaly, which leverages pure Transformer architectures without relying on complex designs, additional modules, or specialized tricks. Given this powerful framework consisted of only Attentions and MLPs, we found four simple components that are essential to multi-class anomaly detection: (1) Foundation Transformers that extracts universal and discriminative features, (2) Noisy Bottleneck where pre-existing Dropouts do all the noise injection tricks, (3) Linear Attention that naturally cannot focus, and (4) Loose Reconstruction that does not force layer-to-layer and point-by-point reconstruction. Extensive experiments are conducted across popular anomaly detection benchmarks including MVTec-AD, VisA, and Real-IAD. Our proposed Dinomaly achieves impressive image-level AUROC of 99.6%, 98.7%, and 89.3% on the three datasets respectively, which is not only superior to state-of-the-art multi-class UAD methods, but also achieves the most advanced class-separated UAD records.

Key facts. Cited by 93 papers in the map (data through 14 Oct 2026). Builds on 58 of its 74 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

58 of 74 references.

References · 58

  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. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  10. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  11. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  12. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
38 more
  1. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 903
  2. 2023Vision Transformers Need Registerscited by 871
  3. 2019On the Convergence of Adam and Beyondcited by 841
  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. 2018Efficient Attention: Attention with Linear Complexitiescited by 368
  12. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  13. 2022BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizerscited by 303
  14. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  15. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  16. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  17. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  18. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  19. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  20. 2023FLatten Transformer: Vision Transformer using Focused Linear Attentioncited by 171
  21. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 160
  22. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  23. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 146
  24. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  25. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  26. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  27. 2022MetaFormer Baselines for Visioncited by 132
  28. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  29. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  30. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  31. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 80
  32. 2023Stable and low-precision training for large-scale vision-language modelscited by 75
  33. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  34. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  35. 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstructioncited by 63
  36. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  37. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  38. 2020DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentationcited by 54

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 28; 2026: 60.

93 papers.

Sort:

By area:

  1. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 48
  2. 2025AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detectioncited by 28
  3. 2025OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoningcited by 18
  4. 2024Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detectioncited by 15
  5. 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
  6. 2025AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detectioncited by 8
  7. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  8. 2025Dinomaly2: A Unified Framework for Unsupervised Image Anomaly Detectioncited by 6
  9. 2024ROADS: Robust Prompt-driven Multi-Class Anomaly Detection under Domain Shiftcited by 5
  10. 2025CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filteringcited by 5
  11. 2025Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmarkcited by 4
  12. 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detectioncited by 4
38 more
  1. 2026Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectivecited by 4
  2. 2024Evaluating lightweight unsupervised online IDS for masquerade attacks in CANcited by 3
  3. 2025GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detectioncited by 3
  4. 2025RoBiS: Robust Binary Segmentation for High-Resolution Industrial Imagescited by 3
  5. 2026A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detectioncited by 3
  6. 2025Unsupervised Defect Detection for Surgical Instrumentscited by 2
  7. 2025ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learningcited by 2
  8. 2025Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Eracited by 2
  9. 2025A Dataset and Baseline for Deep Learning-Based Visual Quality Inspection in Remanufacturingcited by 2
  10. 2025ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categoriescited by 2
  11. 2026GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detectioncited by 2
  12. 2026Is Task-Specific Training Necessary for Anomaly Detection?cited by 2
  13. 2026RAID: Retrieval-Augmented Anomaly Detectioncited by 2
  14. 2026Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Modelscited by 2
  15. 2025HSS-IAD: A Heterogeneous Same-Sort Industrial Anomaly Detection Datasetcited by 1
  16. 2025Learning Multi-view Multi-class Anomaly Detectioncited by 1
  17. 2025Leveraging Learning Bias for Noisy Anomaly Detectioncited by 1
  18. 2025Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Frameworkcited by 1
  19. 2026Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutionscited by 1
  20. 2026MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Modelscited by 1
  21. 2026Memory-Distilled Selection for Noise-Robust Anomaly Detectioncited by 1
  22. 2026IMMoE: Incomplete Multi-View Anomaly Detection via Mixture of View Experts Fusioncited by 1
  23. 2024Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localizationcited by 0
  24. 2024Attention-Guided Perturbation Network for Industrial Anomaly Detectioncited by 0
  25. 2025Pro-AD: Learning Comprehensive Prototypes with Prototype-based Constraint for Multi-class Unsupervised Anomaly Detectioncited by 0
  26. 2025Multi-View Reconstruction with Global Context for 3D Anomaly Detectioncited by 0
  27. 2025Isolating to Harness: Cross-Division Distillation for Fully Unsupervised Anomaly Detectioncited by 0
  28. 2025Diverse Normal Prototypes-Guided Contrastive Reconstruction for Medical Anomaly Detectioncited by 0
  29. 2025Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localizationcited by 0
  30. 2025ShortcutBreaker: Low-Rank Noisy Bottleneck and Frequency Filtering Block for Multi-Class Unsupervised Anomaly Detectioncited by 0
  31. 2025Collaborative Reconstruction and Repair for Multi-class Industrial Anomaly Detectioncited by 0
  32. 2025Physic-HM: Restoring Physical Generative Logic in Multimodal Anomaly Detection via Hierarchical Modulationcited by 0
  33. 2026Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chainingcited by 0
  34. 2026BAAF: Universal Transformation of One-Class Classifiers for Unsupervised Image Anomaly Detectioncited by 0
  35. 2026StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detectioncited by 0
  36. 2026Improving Anomaly Detection with Foundation-Model Synthesis and Wavelet-Domain Attentioncited by 0
  37. 2026Spatial Autoregressive Modeling of DINOv3 Embeddings for Unsupervised Anomaly Detectioncited by 0
  38. 2026MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detectioncited by 0

50 most cited of 93 All 93 (JSON)