{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/diffusionad-denoising-diffusion-for-anomaly","title":"DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection","arxiv_id":"2303.08730","date":"2023-03-15","proceeding":null,"authors":["HUI ZHANG","Zheng Wang","Dan Zeng","Zuxuan Wu","Yu-Gang Jiang"],"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","url_abs":"https://arxiv.org/abs/2303.08730v4","url_pdf":"https://arxiv.org/pdf/2303.08730v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"diffusionad-denoising-diffusion-for-anomaly","repo_url":"https://github.com/huizhang0812/diffusionad","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diffusionad-denoising-diffusion-for-anomaly","repo_url":"https://github.com/HuiZhang0812/DiffusionAD-Denoising-Diffusion-for-Anomaly-Detection","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"unsupervised-anomaly-detection","task_name":"Unsupervised Anomaly Detection"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-mpdd","task":"Anomaly Detection","dataset":"MPDD","model":"DiffusionAD","rank_in_archive_order":9,"of":16,"metrics":{"Detection AUROC":"96.2","Segmentation AUPRO":"95.3","Segmentation AUROC":"98.5"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-visa","task":"Anomaly Detection","dataset":"VisA","model":"DiffusionAD","rank_in_archive_order":7,"of":50,"metrics":{"Detection AUROC":"98.8","Segmentation AUPRO":"96.0","Segmentation AUPRO (until 30% FPR)":"96.0","Segmentation AUROC":"98.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-dagm2007","task":"Unsupervised Anomaly Detection","dataset":"DAGM2007","model":"DiffusionAD","rank_in_archive_order":1,"of":1,"metrics":{"Detection AUROC":"99.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.08730","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}