DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
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. We introduce DiffusionAD, a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network. A fundamental enhancement lies in our reformulation of the reconstruction process using a diffusion model into a noise-to-norm paradigm. Here, the anomalous region loses its distinctive features after being disturbed by Gaussian noise and is subsequently reconstructed into an anomaly-free one. Afterward, the segmentation sub-network predicts pixel-level anomaly scores based on the similarities and discrepancies between the input image and its anomaly-free reconstruction. Additionally, given the substantial decrease in inference speed due to the iterative denoising nature of diffusion models, we revisit the denoising process and introduce a rapid one-step denoising paradigm. This paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality. Furthermore, considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales, enhancing the fidelity of reconstructions. Comprehensive evaluations on four standard and challenging benchmarks reveal that DiffusionAD outperforms current state-of-the-art approaches and achieves comparable inference speed, demonstrating the effectiveness and broad applicability of the proposed pipeline. Code is released at https://github.com/HuiZhang0812/DiffusionAD
- Ganomaly: Semi-supervised anomaly detection via adversarial training. In ACCV, 2018.
- Label-efficient semantic segmentation with diffusion models. In ICLR, 2021.
- Deep autoencoding models for unsupervised anomaly segmentation in brain mr images. In MICCAI, 2019.
- Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection. In CVPR, 2019.
- Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In CVPR, 2020.
- Denoising pretraining for semantic segmentation. In CVPR, 2022.
- Diffusiondet: Diffusion model for object detection. In ICCV, 2023.
- Describing textures in the wild. In CVPR, 2014.
- Sub-image anomaly detection with deep pyramid correspondences. arXiv preprint arXiv:2005.02357, 2020.
- Padim: a patch distribution modeling framework for anomaly detection and localization. In ICPR, 2021.
- Anomaly localization by modeling perceptual features. arXiv preprint arXiv:2008.05369, 2020.
- Iterative energy-based projection on a normal data manifold for anomaly localization. In ICLR, 2019.
- Anomaly detection via reverse distillation from one-class embedding. In CVPR, 2022.
- Diffusion models beat gans on image synthesis. In NeurIPS, 2021.
- Ross Girshick. Fast r-cnn. In ICCV, 2015.
- Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In ICCV, 2019.
- Diffusion models as plug-and-play priors. arXiv preprint arXiv:2206.09012, 2022.
- Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows. In WACV, 2022.
- Deep residual learning for image recognition. In CVPR, 2016.
- Denoising diffusion probabilistic models. In NeurIPS, 2020.
- Divide-and-assemble: Learning block-wise memory for unsupervised anomaly detection. In CVPR, 2021.
- Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions. In ICUMT, 2021.
- Diffusion adversarial representation learning for self-supervised vessel segmentation. arXiv preprint arXiv:2209.14566, 2022.
- Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
- Cfa: Coupled-hypersphere-based feature adaptation for target-oriented anomaly localization. ACCESS, 2022.
- Cutpaste: Self-supervised learning for anomaly detection and localization. In CVPR, 2021.
- Focal loss for dense object detection. In ICCV, 2017.
- Towards visually explaining variational autoencoders. In CVPR, 2020.
- Diversity-measurable anomaly detection. In CVPR, 2023a.
- More control for free! image synthesis with semantic diffusion guidance. In WACV, 2023b.
- Simplenet: A simple network for image anomaly detection and localization. In CVPR, 2023c.
- Ken Perlin. An image synthesizer. ACM SIGGRAPH, 1985.
- Highly accurate dichotomous image segmentation. In ECCV, 2022.
- Self-supervised predictive convolutional attentive block for anomaly detection. In CVPR, 2022.
- High-resolution image synthesis with latent diffusion models. In CVPR, 2022.
- U-net: Convolutional networks for biomedical image segmentation. In MICCAI, 2015.
- Towards total recall in industrial anomaly detection. In CVPR, 2022.
- Same same but differnet: Semi-supervised defect detection with normalizing flows. In WACV, 2021.
- Fully convolutional cross-scale-flows for image-based defect detection. In WACV, 2022.
- Multiresolution knowledge distillation for anomaly detection. In CVPR, 2021.
- Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications. In ICLR, 2017.
- Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In IPMI, 2017.
- Deep unsupervised learning using nonequilibrium thermodynamics. In ICML, 2015.
- Denoising diffusion implicit models. In ICLR, 2020.
- Anoseg: anomaly segmentation network using self-supervised learning. arXiv preprint arXiv:2110.03396, 2021.
- Generative modeling by estimating gradients of the data distribution. In NeurIPS, 2019.
- Improved techniques for training score-based generative models. In NeurIPS, 2020.
- Deep learning for unsupervised anomaly localization in industrial images: A survey. TIM, 2022.
- Revisiting reverse distillation for anomaly detection. In CVPR, 2023.
- Split-brain autoencoder approach for surface defect detection. In ICECCE, 2020.
- Attention is all you need. In NeurIPS, 2017.
- Weakly supervised learning for industrial optical inspection. 2007.
- Anoddpm: Anomaly detection with denoising diffusion probabilistic models using simplex noise. In CVPR Workshop, 2022.
- Memseg: A semi-supervised method for image surface defect detection using differences and commonalities. Eng Appl Artif Intell, 2023.
- Attribute restoration framework for anomaly detection. TMM, 2020.
- Unsupervised pixel-level road defect detection via adversarial image-to-frequency transform. In IV, 2020.
- Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows. arXiv preprint arXiv:2111.07677, 2021.
- Draem-a discriminatively trained reconstruction embedding for surface anomaly detection. In ICCV, 2021.
- Prototypical residual networks for anomaly detection and localization. In CVPR, 2023.
- Spot-the-difference self-supervised pre-training for anomaly detection and segmentation. In ECCV, 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.