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

Test Time Training for Industrial Anomaly Segmentation (2404.03743v1)

Published 4 Apr 2024 in cs.CV

Abstract: Anomaly Detection and Segmentation (AD&S) is crucial for industrial quality control. While existing methods excel in generating anomaly scores for each pixel, practical applications require producing a binary segmentation to identify anomalies. Due to the absence of labeled anomalies in many real scenarios, standard practices binarize these maps based on some statistics derived from a validation set containing only nominal samples, resulting in poor segmentation performance. This paper addresses this problem by proposing a test time training strategy to improve the segmentation performance. Indeed, at test time, we can extract rich features directly from anomalous samples to train a classifier that can discriminate defects effectively. Our general approach can work downstream to any AD&S method that provides an anomaly score map as output, even in multimodal settings. We demonstrate the effectiveness of our approach over baselines through extensive experimentation and evaluation on MVTec AD and MVTec 3D-AD.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv preprint arXiv:1807.02011, 2018.
  2. Mvtec ad – a comprehensive real-world dataset for unsupervised anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  3. 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.
  4. The mvtec 3d-ad dataset for unsupervised 3d anomaly detection and localization. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pages 202–213, 2022.
  5. Informative knowledge distillation for image anomaly segmentation. Knowledge-Based Systems, 248:108846, 2022.
  6. Emerging properties in self-supervised vision transformers. In Proceedings of the International Conference on Computer Vision (ICCV), 2021.
  7. ShapeNet: An Information-Rich 3D Model Repository. Technical Report arXiv:1512.03012 [cs.GR], Stanford University — Princeton University — Toyota Technological Institute at Chicago, 2015.
  8. Self-supervised normalizing flows for image anomaly detection and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2926–2935, 2023.
  9. To adapt or not to adapt? real-time adaptation for semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16548–16559, 2023.
  10. Multimodal industrial anomaly detection by crossmodal feature mapping. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024.
  11. Padim: a patch distribution modeling framework for anomaly detection and localization. In International Conference on Pattern Recognition, pages 475–489. Springer, 2021.
  12. Anomaly detection via reverse distillation from one-class embedding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9737–9746, 2022.
  13. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  14. Test time adaptation via conjugate pseudo-labels. Advances in Neural Information Processing Systems, 35:6204–6218, 2022.
  15. 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.
  16. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16000–16009, 2022.
  17. Back to the feature: classical 3d features are (almost) all you need for 3d anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2967–2976, 2023.
  18. 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.
  19. Test-time classifier adjustment module for model-agnostic domain generalization. Advances in Neural Information Processing Systems, 34:2427–2440, 2021.
  20. Single image test-time adaptation for segmentation. arXiv preprint arXiv:2309.14052, 2023.
  21. Fr-patchcore: An industrial anomaly detection method for improving generalization. Sensors, 24(5), 2024.
  22. Sita: Single image test-time adaptation. arXiv preprint arXiv:2112.02355, 2021.
  23. Ev-tta: Test-time adaptation for event-based object recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17745–17754, 2022.
  24. Segment anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 4015–4026, 2023.
  25. 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.
  26. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In International conference on machine learning, pages 6028–6039. PMLR, 2020.
  27. Deep industrial image anomaly detection: A survey. arXiv preprint arXiv:2301.11514, 2, 2023.
  28. Mocca: Multilayer one-class classification for anomaly detection. IEEE Transactions on Neural Networks and Learning Systems, 33(6):2313–2323, 2021.
  29. Evaluating prediction-time batch normalization for robustness under covariate shift. arXiv preprint arXiv:2006.10963, 2020.
  30. Tipi: Test time adaptation with transformation invariance. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 24162–24171, 2023.
  31. Efficient test-time model adaptation without forgetting. In International conference on machine learning, pages 16888–16905. PMLR, 2022.
  32. Dinov2: Learning robust visual features without supervision, 2023.
  33. Masked autoencoders for point cloud self-supervised learning. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part II, pages 604–621. Springer, 2022.
  34. Inpainting transformer for anomaly detection. In International Conference on Image Analysis and Processing, pages 394–406. Springer, 2022.
  35. Panda: Adapting pretrained features for anomaly detection and segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2806–2814, 2021.
  36. Modeling the distribution of normal data in pre-trained deep features for anomaly detection. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 6726–6733. IEEE, 2021.
  37. Self-supervised predictive convolutional attentive block for anomaly detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13576–13586, 2022.
  38. Towards total recall in industrial anomaly detection. In Proceedings of 2022 IEEE Conference on Computer Vision and Pattern Recognition, pages 14298–14308, 2022.
  39. 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.
  40. Multiresolution knowledge distillation for anomaly detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14902–14912, 2021.
  41. Learning and evaluating representations for deep one-class classification. In International Conference on Learning Representations, 2021.
  42. Test-time training with self-supervision for generalization under distribution shifts. In International conference on machine learning, pages 9229–9248. PMLR, 2020.
  43. Tent: Fully test-time adaptation by entropy minimization. In International Conference on Learning Representations, 2020.
  44. Student-teacher feature pyramid matching for anomaly detection. In The British Machine Vision Conference (BMVC), 2021.
  45. Support vector machine classifier via l0/1subscript𝑙01l_{0/1}italic_l start_POSTSUBSCRIPT 0 / 1 end_POSTSUBSCRIPTl0/1 soft-margin loss. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10):7253–7265, 2022.
  46. Deep visual domain adaptation: A survey. Neurocomputing, 312:135–153, 2018.
  47. Multimodal industrial anomaly detection via hybrid fusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8032–8041, 2023.
  48. Anoddpm: Anomaly detection with denoising diffusion probabilistic models using simplex noise. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 650–656, 2022.
  49. Dfr: Deep feature reconstruction for unsupervised anomaly segmentation. arXiv preprint arXiv:2012.07122, 2020.
  50. Memseg: A semi-supervised method for image surface defect detection using differences and commonalities. Engineering Applications of Artificial Intelligence, 119:105835, 2023.
  51. Patch svdd: Patch-level svdd for anomaly detection and segmentation. In Proceedings of the Asian conference on computer vision, 2020.
  52. Self-supervised learning for anomaly detection with dynamic local augmentation. IEEE Access, 9:147201–147211, 2021.
  53. Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows. arXiv preprint arXiv:2111.07677, 2021.
  54. Wide residual networks. In BMVC, 2016.
  55. 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.
  56. Anomaly detection using improved deep svdd model with data structure preservation. Pattern Recognition Letters, 148:1–6, 2021.
  57. Point transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16259–16268, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Alex Costanzino (8 papers)
  2. Pierluigi Zama Ramirez (31 papers)
  3. Mirko Del Moro (1 paper)
  4. Agostino Aiezzo (1 paper)
  5. Giuseppe Lisanti (19 papers)
  6. Samuele Salti (34 papers)
  7. Luigi Di Stefano (54 papers)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets