Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing (2301.13359v5)

Published 31 Jan 2023 in cs.CV and cs.AI

Abstract: Image anomaly detection (IAD) is an emerging and vital computer vision task in industrial manufacturing (IM). Recently, many advanced algorithms have been reported, but their performance deviates considerably with various IM settings. We realize that the lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-world applications. In addition, it is difficult for researchers to analyze IAD algorithms without a uniform benchmark. To solve this problem, we propose a uniform IM benchmark, for the first time, to assess how well these algorithms perform, which includes various levels of supervision (unsupervised versus fully supervised), learning paradigms (few-shot, continual and noisy label), and efficiency (memory usage and inference speed). Then, we construct a comprehensive image anomaly detection benchmark (IM-IAD), which includes 19 algorithms on seven major datasets with a uniform setting. Extensive experiments (17,017 total) on IM-IAD provide in-depth insights into IAD algorithm redesign or selection. Moreover, the proposed IM-IAD benchmark challenges existing algorithms and suggests future research directions. To foster reproducibility and accessibility, the source code of IM-IAD is uploaded on the website, https://github.com/M-3LAB/IM-IAD.

View on arXiv
Definition Search Book Streamline Icon: https://streamlinehq.com
References (94)
  1. Efficientad: Accurate visual anomaly detection at millisecond-level latencies. ArXiv, abs/2303.14535, 2023.
  2. The mvtec anomaly detection dataset: a comprehensive real-world dataset for unsupervised anomaly detection. International Journal of Computer Vision, 129(4):1038–1059, 2021.
  3. Beyond dents and scratches: Logical constraints in unsupervised anomaly detection and localization. International Journal of Computer Vision, 130(4):947–969, 2022.
  4. Mvtec ad — a comprehensive real-world dataset for unsupervised anomaly detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9584–9592, 2019.
  5. Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4183–4192, 2020.
  6. The mvtec 3d-ad dataset for unsupervised 3d anomaly detection and localization. arXiv preprint arXiv:2112.09045, 2021.
  7. Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv preprint arXiv:1807.02011, 2018.
  8. The eyecandies dataset for unsupervised multimodal anomaly detection and localization. In Asian Conference on Computer Vision, 2022.
  9. Segment any anomaly without training via hybrid prompt regularization. arXiv preprint arXiv:2305.10724, 2023.
  10. Riemannian walk for incremental learning: Understanding forgetting and intransigence. ArXiv, abs/1801.10112, 2018.
  11. Deep one-class classification via interpolated gaussian descriptor. In AAAI, 2022.
  12. Deep one-class classification via interpolated gaussian descriptor. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1):383–392, 2022.
  13. Image block augmentation for one-shot learning. In AAAI Conference on Artificial Intelligence, 2019.
  14. Neural batch sampling with reinforcement learning for semi-supervised anomaly detection. In European conference on computer vision, pages 751–766. Springer, 2020.
  15. Sub-image anomaly detection with deep pyramid correspondences. arXiv preprint arXiv:2005.02357, 2020.
  16. Improved anomaly detection by training an autoencoder with skip connections on images corrupted with stain-shaped noise. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 7915–7922. IEEE, 2021.
  17. Data refinement for fully unsupervised visual inspection using pre-trained networks. arXiv preprint arXiv:2202.12759, 2022.
  18. German chapter of the IAPR (International Association for Pattern Recognition)) DAGM (Deutsche Arbeitsgemeinschaft für Mustererkennung e.V. and the GNSS (German Chapter of the European Neural Network Society). Dagm dataset. http://www.thisisurl/, 2000.
  19. Puck de Haan and Sindy Löwe. Contrastive predictive coding for anomaly detection. arXiv preprint arXiv:2107.07820, 2021.
  20. Padim: a patch distribution modeling framework for anomaly detection and localization. In International Conference on Pattern Recognition, pages 475–489. Springer, 2021.
  21. Anomaly localization by modeling perceptual features. ArXiv, abs/2008.05369, 2020.
  22. Iterative energy-based projection on a normal data manifold for anomaly localization. In International Conference on Learning Representations, 2019.
  23. Anomaly detection via reverse distillation from one-class embedding. ArXiv, abs/2201.10703, 2022.
  24. A survey of methods for automated quality control based on images. International Journal of Computer Vision, 131:2553 – 2581, 2023.
  25. Catching both gray and black swans: Open-set supervised anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7388–7398, 2022.
  26. An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv, abs/2010.11929, 2020.
  27. Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 98–107, 2022.
  28. Adbench: Anomaly detection benchmark. ArXiv, abs/2206.09426, 2022.
  29. Divide-and-assemble: Learning block-wise memory for unsupervised anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8791–8800, 2021.
  30. A semantic-enhanced method based on deep svdd for pixel-wise anomaly detection. In 2021 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE, 2021.
  31. Registration based few-shot anomaly detection. arXiv preprint arXiv:2207.07361, 2022.
  32. Surface defect saliency of magnetic tile. The Visual Computer, 36(1):85–96, 2020.
  33. Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions. In 2021 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), pages 66–71. IEEE, 2021.
  34. Masked swin transformer unet for industrial anomaly detection. IEEE Transactions on Industrial Informatics, 2022.
  35. Softpatch: Unsupervised anomaly detection with noisy data. Advances in Neural Information Processing Systems, 35:15433–15445, 2022.
  36. Anomaly detection of defect using energy of point pattern features within random finite set framework. arXiv preprint arXiv:2108.12159, 2021.
  37. Semi-orthogonal embedding for efficient unsupervised anomaly segmentation. arXiv preprint arXiv:2105.14737, 2021.
  38. Segment anything. arXiv preprint arXiv:2304.02643, 2023.
  39. Normalizing flows: Introduction and ideas. ArXiv, abs/1908.09257, 2019.
  40. Cfa: Coupled-hypersphere-based feature adaptation for target-oriented anomaly localization. arXiv preprint arXiv:2206.04325, 2022.
  41. Fabric defect detection in textile manufacturing: a survey of the state of the art. Security and Communication Networks, 2021:1–13, 2021.
  42. Cutpaste: Self-supervised learning for anomaly detection and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9664–9674, 2021.
  43. Efficient anomaly detection with budget annotation using semi-supervised residual transformer. arXiv preprint arXiv:2306.03492, 2023.
  44. Anomaly detection via self-organizing map. In 2021 IEEE International Conference on Image Processing (ICIP), pages 974–978. IEEE, 2021.
  45. Towards continual adaptation in industrial anomaly detection. In Proceedings of the 30th ACM International Conference on Multimedia, pages 2871–2880, 2022.
  46. Deep industrial image anomaly detection: A survey. arXiv preprint arXiv:2301.11514, 2, 2023.
  47. Classification with noisy labels by importance reweighting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38:447–461, 2014.
  48. Towards visually explaining variational autoencoders. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8642–8651, 2020.
  49. Simplenet: A simple network for image anomaly detection and localization. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20402–20411, 2023.
  50. Explainable deep one-class classification. In International Conference on Learning Representations, 2020.
  51. Mocca: Multilayer one-class classification for anomaly detection. IEEE Transactions on Neural Networks and Learning Systems, 2021.
  52. Vt-adl: A vision transformer network for image anomaly detection and localization. In 2021 IEEE 30th International Symposium on Industrial Electronics (ISIE), pages 01–06. IEEE, 2021.
  53. Data augmentation for meta-learning. In International Conference on Machine Learning, 2020.
  54. Explainable deep few-shot anomaly detection with deviation networks. arXiv preprint arXiv:2108.00462, 2021.
  55. Inpainting transformer for anomaly detection. In International Conference on Image Analysis and Processing, pages 394–406. Springer, 2022.
  56. Latent outlier exposure for anomaly detection with contaminated data. arXiv preprint arXiv:2202.08088, 2022.
  57. Visual structural assessment and anomaly detection for high-velocity data streams. IEEE Transactions on Cybernetics, 51:5979–5992, 2020.
  58. Panda: Adapting pretrained features for anomaly detection and segmentation. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2805–2813, 2021.
  59. Experience replay for continual learning. In NeurIPS, 2019.
  60. Towards total recall in industrial anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14318–14328, 2022.
  61. Same same but differnet: Semi-supervised defect detection with normalizing flows. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 1907–1916, 2021.
  62. Fully convolutional cross-scale-flows for image-based defect detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1088–1097, 2022.
  63. Multiresolution knowledge distillation for anomaly detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14902–14912, 2021.
  64. Defect detection of metal nuts applying convolutional neural networks. In 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), pages 248–257. IEEE, 2021.
  65. Self-supervised out-of-distribution detection and localization with natural synthetic anomalies (nsa). arXiv preprint arXiv:2109.15222, 2021.
  66. Active learning for convolutional neural networks: A core-set approach. arXiv: Machine Learning, 2018.
  67. A hierarchical transformation-discriminating generative model for few shot anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8495–8504, 2021.
  68. Learning and evaluating representations for deep one-class classification. In International Conference on Learning Representations, 2020.
  69. Selfie: Refurbishing unclean samples for robust deep learning. In International Conference on Machine Learning, 2019.
  70. Trustmae: A noise-resilient defect classification framework using memory-augmented auto-encoders with trust regions. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 276–285, 2021.
  71. Deep learning for unsupervised anomaly localization in industrial images: A survey. IEEE Transactions on Instrumentation and Measurement, 71:1–21, 2022.
  72. Fabric inspection based on the elo rating method. Pattern Recognition, 51:378–394, 2016.
  73. Attention guided anomaly localization in images. In European Conference on Computer Vision, pages 485–503. Springer, 2020.
  74. Student-teacher feature pyramid matching for anomaly detection. In BMVC, 2021.
  75. Dynamic fusion module evolves drivable area and road anomaly detection: A benchmark and algorithms. IEEE transactions on cybernetics, 52(10):10750–10760, 2021.
  76. Hybrid variable monitoring mixture model for anomaly detection in industrial processes. IEEE transactions on cybernetics, PP, 2022.
  77. Pushing the limits of fewshot anomaly detection in industry vision: Graphcore. In The Eleventh International Conference on Learning Representations, 2023.
  78. Reconstruction student with attention for student-teacher pyramid matching. arXiv preprint arXiv:2111.15376, 2021.
  79. Learning semantic context from normal samples for unsupervised anomaly detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 3110–3118, 2021.
  80. Unsupervised anomaly segmentation via multilevel image reconstruction and adaptive attention-level transition. IEEE Transactions on Instrumentation and Measurement, 70:1–12, 2021.
  81. Dfr: Deep feature reconstruction for unsupervised anomaly segmentation. arXiv preprint arXiv:2012.07122, 2020.
  82. Explicit boundary guided semi-push-pull contrastive learning for supervised anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 24490–24499, 2023.
  83. Patch svdd: Patch-level svdd for anomaly detection and segmentation. In Proceedings of the Asian Conference on Computer Vision, 2020.
  84. Convolutional recurrent reconstructive network for spatiotemporal anomaly detection in solder paste inspection. IEEE Transactions on Cybernetics, 52:4688–4700, 2019.
  85. Self-supervise, refine, repeat: Improving unsupervised anomaly detection. 2021.
  86. Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows. arXiv preprint arXiv:2111.07677, 2021.
  87. Wide residual networks. In Procedings of the British Machine Vision Conference 2016. British Machine Vision Association, 2016.
  88. Draem-a discriminatively trained reconstruction embedding for surface anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8330–8339, 2021.
  89. Reconstruction by inpainting for visual anomaly detection. Pattern Recognition, 112:107706, 2021.
  90. Dsr–a dual subspace re-projection network for surface anomaly detection. arXiv preprint arXiv:2208.01521, 2022.
  91. Prototypical residual networks for anomaly detection and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16281–16291, 2023.
  92. Pku-goodsad: A supermarket goods dataset for unsupervised anomaly detection and segmentation. arXiv preprint arXiv:2307.04956, 2023.
  93. Benchmarking unsupervised anomaly detection and localization. ArXiv, abs/2205.14852, 2022.
  94. Spot-the-difference self-supervised pre-training for anomaly detection and segmentation. arXiv preprint arXiv:2207.14315, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Guoyang Xie (21 papers)
  2. Jinbao Wang (30 papers)
  3. Jiaqi Liu (102 papers)
  4. Jiayi Lyu (9 papers)
  5. Yong Liu (721 papers)
  6. Chengjie Wang (178 papers)
  7. Feng Zheng (117 papers)
  8. Yaochu Jin (108 papers)
Citations (48)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - M-3LAB/IM-IAD (23 stars)