mlsanityData to 14 Oct 2026

Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders

arXiv 1807.02011 ↗First posted 5 Jul 2018cs.CV cs.LGcited by 264

Not on the map. Why?

Abstract (arXiv)

Convolutional autoencoders have emerged as popular methods for unsupervised defect segmentation on image data. Most commonly, this task is performed by thresholding a pixel-wise reconstruction error based on an ℓp distance. This procedure, however, leads to large residuals whenever the reconstruction encompasses slight localization inaccuracies around edges. It also fails to reveal defective regions that have been visually altered when intensity values stay roughly consistent. We show that these problems prevent these approaches from being applied to complex real-world scenarios and that it cannot be easily avoided by employing more elaborate architectures such as variational or feature matching autoencoders. We propose to use a perceptual loss function based on structural similarity which examines inter-dependencies between local image regions, taking into account luminance, contrast and structural information, instead of simply comparing single pixel values. It achieves significant performance gains on a challenging real-world dataset of nanofibrous materials and a novel dataset of two woven fabrics over the state of the art approaches for unsupervised defect segmentation that use pixel-wise reconstruction error metrics.

Key facts. Cited by 264 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 33; 2022: 51; 2023: 51; 2024: 61; 2025: 35; 2026: 33.

264 papers.

Sort:

By area:

  1. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  2. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  3. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  4. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  5. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  6. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  7. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  8. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  9. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 160
  10. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  11. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  12. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 146
38 more
  1. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  2. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  3. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  4. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  5. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  6. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 90
  7. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 82
  8. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 80
  9. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  10. 2023PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flowcited by 74
  11. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  12. 2022MemSeg: A semi-supervised method for image surface defect detection using differences and commonalitiescited by 68
  13. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 68
  14. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  15. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  16. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  17. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  18. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  19. 2022The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localizationcited by 57
  20. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 57
  21. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  22. 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
  23. 2023Advances in Deep Concealed Scene Understandingcited by 47
  24. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  25. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  26. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detectioncited by 43
  27. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 42
  28. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detectioncited by 42
  29. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  30. 2022ADTR: Anomaly Detection Transformer with Feature Reconstructioncited by 31
  31. 2025The MVTec AD 2 Dataset: Advanced Scenarios for Unsupervised Anomaly Detectioncited by 30
  32. 2022AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decodercited by 29
  33. 2021Autoencoding Under Normalization Constraintscited by 26
  34. 2021Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentationcited by 26
  35. 2024MedIAnomaly: A comparative study of anomaly detection in medical imagescited by 26
  36. 2023MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detectioncited by 25
  37. 2023An Incremental Unified Framework for Small Defect Inspectioncited by 25
  38. 2024ResAD: A Simple Framework for Class Generalizable Anomaly Detectioncited by 25

50 most cited of 264 All 264 (JSON)