Papers › AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for...
AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection
Yeongmin Kim, Huiwon Jang, DongKeon Lee, Ho-Jin Choi
Unsupervised anomaly detection is coming into the spotlight these days in various practical domains due to the limited amount of anomaly data. One of the major approaches for it is a normalizing flow which pursues the invertible transformation of a complex distribution as images into an easy distribution as N(0, I). In fact, algorithms based on normalizing flow like FastFlow and CFLOW-AD establish state-of-the-art performance on unsupervised anomaly detection tasks. Nevertheless, we investigate these algorithms convert normal images into not N(0, I) as their destination, but an arbitrary normal distribution. Moreover, their performances are often unstable, which is highly critical for unsupervised tasks because data for validation are not provided. To break through these observations, we propose a simple solution AltUB which introduces alternating training to update the base distribution of normalizing flow for anomaly detection. AltUB effectively improves the stability of performance of normalizing flow. Furthermore, our method achieves the new state-of-the-art performance of the anomaly segmentation task on the MVTec AD dataset with 98.8% AUROC.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 | FastFlow+AltUB | Segmentation AUROC | 98.2 | #12 of 15 | Archive leaderboard | report |
| Anomaly Detection | MVTec AD | CFLOW-AD+AltUB | Detection AUROC | 99.4 | #37 of 148 | Archive leaderboard | report |
| Anomaly Detection | MVTec AD | CFLOW-AD+AltUB | Segmentation AUROC | 98.5 | #37 of 148 | Archive leaderboard | report |
| Anomaly Detection | MVTec AD | FastFlow+AltUB | Segmentation AUROC | 98.83 | #133 of 148 | 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.
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