Papers › Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection
Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection
Justin Tebbe, Jawad Tayyub
Diffusion models have found valuable applications in anomaly detection by capturing the nominal data distribution and identifying anomalies via reconstruction. Despite their merits, they struggle to localize anomalies of varying scales, especially larger anomalies such as entire missing components. Addressing this, we present a novel framework that enhances the capability of diffusion models, by extending the previous introduced implicit conditioning approach Meng et al. (2022) in three significant ways. First, we incorporate a dynamic step size computation that allows for variable noising steps in the forward process guided by an initial anomaly prediction. Second, we demonstrate that denoising an only scaled input, without any added noise, outperforms conventional denoising process. Third, we project images in a latent space to abstract away from fine details that interfere with reconstruction of large missing components. Additionally, we propose a fine-tuning mechanism that facilitates the model to effectively grasp the nuances of the target domain. Our method undergoes rigorous evaluation on prominent anomaly detection datasets VisA, BTAD and MVTec yielding strong performance. Importantly, our framework effectively localizes anomalies regardless of their scale, marking a pivotal advancement in diffusion-based anomaly detection.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Anomaly Detection | BTAD | D3AD | Detection AUROC | 95.2 | #8 of 15 | Archive leaderboard | report |
| Anomaly Detection | BTAD | D3AD | Segmentation AUPRO | 83.2 | #8 of 15 | Archive leaderboard | report |
| Anomaly Detection | VisA | D3AD | Detection AUROC | 96.0 | #20 of 50 | Archive leaderboard | report |
| Anomaly Detection | VisA | D3AD | Segmentation AUPRO (until 30% FPR) | 94.1 | #20 of 50 | Archive leaderboard | report |
| Anomaly Detection | VisA | D3AD | Segmentation AUROC | 97.9 | #20 of 50 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections