mlsanityData to 7 Oct 2026

Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detection

arXiv 2503.23451 ↗First posted 30 Mar 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Anomaly detection (AD) is essential for automating visual inspection in manufacturing. This field of computer vision is rapidly evolving, with increasing attention towards real-world applications. Meanwhile, popular datasets are typically produced in controlled lab environments with artificially created defects, unable to capture the diversity of real production conditions. New methods often fail in production settings, showing significant performance degradation or requiring impractical computational resources. This disconnect between academic results and industrial viability threatens to misdirect visual anomaly detection research. This paper makes three key contributions: (1) we demonstrate the importance of real-world datasets and establish benchmarks using actual production data, (2) we provide a fair comparison of existing SOTA methods across diverse tasks by utilizing metrics that are valuable for practical applications, and (3) we present a comprehensive analysis of recent advancements in this field by discussing important challenges and new perspectives for bridging the academia-industry gap. The code is publicly available at https://github.com/abc-125/viad-benchmark

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 64 of its 80 references that are in the map. First posted on arXiv 30 Mar 2025.

Builds on

64 of 80 references.

References · 64

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2023Segment Anythingcited by 8,158
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2016Wide Residual Networkscited by 3,057
  8. 2015Variational Inference with Normalizing Flowscited by 2,161
  9. 2013Describing Textures in the Wildcited by 2,110
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  11. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  12. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
38 more
  1. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  2. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  3. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  4. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  5. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  6. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  7. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  8. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  9. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  10. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  11. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
  12. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  13. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  14. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  15. 2019Deep Anomaly Detection with Deviation Networkscited by 152
  16. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  17. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  18. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  19. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  20. 2023APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot ADcited by 128
  21. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  22. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  23. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  24. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 115
  25. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  26. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  27. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 97
  28. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  29. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
  30. 2022Anomalib: A Deep Learning Library for Anomaly Detectioncited by 75
  31. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  32. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  33. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  34. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  35. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  36. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  37. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  38. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48

50 most cited of 64 All 64 (JSON)

Built on by

Not cited yet.