mlsanityData to 14 Oct 2026

Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale Reconstruction

arXiv 2304.02216 ↗First posted 5 Apr 2023cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Industrial anomaly detection (IAD) is crucial for automating industrial quality inspection. The diversity of the datasets is the foundation for developing comprehensive IAD algorithms. Existing IAD datasets focus on the diversity of data categories, overlooking the diversity of domains within the same data category. In this paper, to bridge this gap, we propose the Aero-engine Blade Anomaly Detection (AeBAD) dataset, consisting of two sub-datasets: the single-blade dataset and the video anomaly detection dataset of blades. Compared to existing datasets, AeBAD has the following two characteristics: 1.) The target samples are not aligned and at different scales. 2.) There is a domain shift between the distribution of normal samples in the test set and the training set, where the domain shifts are mainly caused by the changes in illumination and view. Based on this dataset, we observe that current state-of-the-art (SOTA) IAD methods exhibit limitations when the domain of normal samples in the test set undergoes a shift. To address this issue, we propose a novel method called masked multi-scale reconstruction (MMR), which enhances the model's capacity to deduce causality among patches in normal samples by a masked reconstruction task. MMR achieves superior performance compared to SOTA methods on the AeBAD dataset. Furthermore, MMR achieves competitive performance with SOTA methods to detect the anomalies of different types on the MVTec AD dataset. Code and dataset are available at https://github.com/zhangzilongc/MMR.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 5 Apr 2023.

Builds on

35 of 51 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  6. 2016Layer Normalizationcited by 5,669
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  9. 2016Wide Residual Networkscited by 3,070
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  11. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  12. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
23 more
  1. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  2. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  3. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  4. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  5. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  6. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  7. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  8. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  9. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  10. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  11. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  12. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  13. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  14. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  15. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  16. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 68
  17. 2020DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentationcited by 54
  18. 2020Iterative energy-based projection on a normal data manifold for anomaly localizationcited by 47
  19. 2021OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Imagescited by 46
  20. 2022A Survey of Visual Sensory Anomaly Detectioncited by 11
  21. 2018Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexitycited by 10
  22. 2022WaferSegClassNet -- A Light-weight Network for Classification and Segmentation of Semiconductor Wafer Defectscited by 7
  23. 2023Steerable Equivariant Representation Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 4; 2026: 9.

23 papers.

Sort:

By area:

  1. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  2. 2023Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semanticscited by 16
  3. 2023InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Imagescited by 15
  4. 2024AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarioscited by 9
  5. 2024ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detectioncited by 7
  6. 2024Small Object Few-shot Segmentation for Vision-based Industrial Inspectioncited by 5
  7. 2025Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmarkcited by 4
  8. 2023Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Studycited by 3
  9. 2024IPAD: Industrial Process Anomaly Detection Datasetcited by 3
  10. 2024MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detectioncited by 3
  11. 2023Noise-to-Norm Reconstruction for Industrial Anomaly Detection and Localizationcited by 1
  12. 2025Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detectioncited by 1
11 more
  1. 2025Hybrid Synthetic Data Generation with Domain Randomization Enables Zero-Shot Vision-Based Part Inspection Under Extreme Class Imbalancecited by 1
  2. 2026SPARC: Subspace Position-Aware Robust Few-Shot Calibration for Distribution-Shifted Industrial Anomaly Detectioncited by 1
  3. 2025ProtoAnomalyNCD: Prototype Learning for Multi-class Novel Anomaly Discovery in Industrial Scenarioscited by 0
  4. 2026Synthetic Defect Image Generation for Power Line Insulator Inspection Using Multimodal Large Language Modelscited by 0
  5. 2026Contrastive Augmented Transformer with Domain-specific Enhancement for Robust Multi-scenario Metal Surface Defect Detectioncited by 0
  6. 2026Visual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervisioncited by 0
  7. 2026ShiftSplit-AD: Separating Domain Shift from Defects in Foundation-Feature Visual Anomaly Detectioncited by 0
  8. 2026NFAD: Nuisance-Filtered Anomaly Detection Under Distribution Shiftcited by 0
  9. 2026Focus and Supplement: Dual-Enhanced Vision Transformer for Multi-Class Anomaly Classificationcited by 0
  10. 2026Robust Online Aero-Engine Blade Defect Detection via Dual-Alignment Test-Time Adaptationcited by 0
  11. 2026Robust Logical Anomaly Detection under Capture Shifts via Synthetic Anomaliescited by 0