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

DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection (2303.08730v3)

Published 15 Mar 2023 in cs.CV

Abstract: Anomaly detection has garnered extensive applications in real industrial manufacturing due to its remarkable effectiveness and efficiency. However, previous generative-based models have been limited by suboptimal reconstruction quality, hampering their overall performance. A fundamental enhancement lies in our reformulation of the reconstruction process using a diffusion model into a noise-to-norm paradigm. Here, anomalous regions are perturbed with Gaussian noise and reconstructed as normal, overcoming the limitations of previous models by facilitating anomaly-free restoration. Additionally, we propose a rapid one-step denoising paradigm, significantly faster than the traditional iterative denoising in diffusion models. Furthermore, the introduction of the norm-guided paradigm elevates the accuracy and fidelity of reconstructions. The segmentation sub-network predicts pixel-level anomaly scores using the input image and its anomaly-free restoration. Comprehensive evaluations on four standard and challenging benchmarks reveal that DiffusionAD outperforms current state-of-the-art approaches, demonstrating the effectiveness and broad applicability of the proposed pipeline.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Ganomaly: Semi-supervised anomaly detection via adversarial training. In ACCV, 2018.
  2. Label-efficient semantic segmentation with diffusion models. In ICLR, 2021.
  3. Deep autoencoding models for unsupervised anomaly segmentation in brain mr images. In MICCAI, 2019.
  4. Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection. In CVPR, 2019.
  5. Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In CVPR, 2020.
  6. Denoising pretraining for semantic segmentation. In CVPR, 2022.
  7. Diffusiondet: Diffusion model for object detection. In ICCV, 2023.
  8. Describing textures in the wild. In CVPR, 2014.
  9. Sub-image anomaly detection with deep pyramid correspondences. arXiv preprint arXiv:2005.02357, 2020.
  10. Padim: a patch distribution modeling framework for anomaly detection and localization. In ICPR, 2021.
  11. Anomaly localization by modeling perceptual features. arXiv preprint arXiv:2008.05369, 2020.
  12. Iterative energy-based projection on a normal data manifold for anomaly localization. In ICLR, 2019.
  13. Anomaly detection via reverse distillation from one-class embedding. In CVPR, 2022.
  14. Diffusion models beat gans on image synthesis. In NeurIPS, 2021.
  15. Ross Girshick. Fast r-cnn. In ICCV, 2015.
  16. Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In ICCV, 2019.
  17. Diffusion models as plug-and-play priors. arXiv preprint arXiv:2206.09012, 2022.
  18. Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows. In WACV, 2022.
  19. Deep residual learning for image recognition. In CVPR, 2016.
  20. Denoising diffusion probabilistic models. In NeurIPS, 2020.
  21. Divide-and-assemble: Learning block-wise memory for unsupervised anomaly detection. In CVPR, 2021.
  22. Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions. In ICUMT, 2021.
  23. Diffusion adversarial representation learning for self-supervised vessel segmentation. arXiv preprint arXiv:2209.14566, 2022.
  24. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  25. Cfa: Coupled-hypersphere-based feature adaptation for target-oriented anomaly localization. ACCESS, 2022.
  26. Cutpaste: Self-supervised learning for anomaly detection and localization. In CVPR, 2021.
  27. Focal loss for dense object detection. In ICCV, 2017.
  28. Towards visually explaining variational autoencoders. In CVPR, 2020.
  29. Diversity-measurable anomaly detection. In CVPR, 2023a.
  30. More control for free! image synthesis with semantic diffusion guidance. In WACV, 2023b.
  31. Simplenet: A simple network for image anomaly detection and localization. In CVPR, 2023c.
  32. Ken Perlin. An image synthesizer. ACM SIGGRAPH, 1985.
  33. Highly accurate dichotomous image segmentation. In ECCV, 2022.
  34. Self-supervised predictive convolutional attentive block for anomaly detection. In CVPR, 2022.
  35. High-resolution image synthesis with latent diffusion models. In CVPR, 2022.
  36. U-net: Convolutional networks for biomedical image segmentation. In MICCAI, 2015.
  37. Towards total recall in industrial anomaly detection. In CVPR, 2022.
  38. Same same but differnet: Semi-supervised defect detection with normalizing flows. In WACV, 2021.
  39. Fully convolutional cross-scale-flows for image-based defect detection. In WACV, 2022.
  40. Multiresolution knowledge distillation for anomaly detection. In CVPR, 2021.
  41. Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications. In ICLR, 2017.
  42. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In IPMI, 2017.
  43. Deep unsupervised learning using nonequilibrium thermodynamics. In ICML, 2015.
  44. Denoising diffusion implicit models. In ICLR, 2020.
  45. Anoseg: anomaly segmentation network using self-supervised learning. arXiv preprint arXiv:2110.03396, 2021.
  46. Generative modeling by estimating gradients of the data distribution. In NeurIPS, 2019.
  47. Improved techniques for training score-based generative models. In NeurIPS, 2020.
  48. Deep learning for unsupervised anomaly localization in industrial images: A survey. TIM, 2022.
  49. Revisiting reverse distillation for anomaly detection. In CVPR, 2023.
  50. Split-brain autoencoder approach for surface defect detection. In ICECCE, 2020.
  51. Attention is all you need. In NeurIPS, 2017.
  52. Weakly supervised learning for industrial optical inspection. 2007.
  53. Anoddpm: Anomaly detection with denoising diffusion probabilistic models using simplex noise. In CVPR Workshop, 2022.
  54. Memseg: A semi-supervised method for image surface defect detection using differences and commonalities. Eng Appl Artif Intell, 2023.
  55. Attribute restoration framework for anomaly detection. TMM, 2020.
  56. Unsupervised pixel-level road defect detection via adversarial image-to-frequency transform. In IV, 2020.
  57. Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows. arXiv preprint arXiv:2111.07677, 2021.
  58. Draem-a discriminatively trained reconstruction embedding for surface anomaly detection. In ICCV, 2021.
  59. Prototypical residual networks for anomaly detection and localization. In CVPR, 2023.
  60. Spot-the-difference self-supervised pre-training for anomaly detection and segmentation. In ECCV, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Hui Zhang (405 papers)
  2. Zheng Wang (400 papers)
  3. Zuxuan Wu (144 papers)
  4. Yu-Gang Jiang (223 papers)
Citations (8)
View on Semantic Scholar

Summary

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

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

YouTube