Papers › Making Anomalies More Anomalous: Video Anomaly Detection Using a Novel Generator and Destroyer

Making Anomalies More Anomalous: Video Anomaly Detection Using a Novel Generator and Destroyer

26 Feb 2024journal 2024 2archive 2025-07-28

Seungkyun Hong*, Sunghyun Ahn*, Youngwan Jo and Sanghyun Park

We propose a novel approach for video anomaly detection. Existing video anomaly detection methods train only on normal frames, with the expectation that the quality of the abnormal frames will decrease, and utilize the reconstruction error with the ground truth to detect anomalies. However, a challenge exists owing to the powerful generalization capability of deep neural networks, as they tend to proficiently generate abnormal frames. To address this issue, we introduce a novel method to make anomalies more anomalous by destroying abnormal areas in abnormal frames. Accordingly, we propose the frame-to-label and motion (F2LM) generator and Destroyer. The F2LM generator predicts a future frame by utilizing the label and motion information of the input frames, thereby degrading the quality of abnormal regions. The Destroyer destroys abnormal regions by transforming low-quality areas into zero vectors. Both models were trained individually, and during testing, the F2LM generator degraded the quality of abnormal regions, and the Destroyer subsequently destroyed these areas. Our proposed video anomaly detection method demonstrated superior performance compared to state-of-the-art models with three benchmark datasets (UCSD Ped2, CUHK Avenue, Shanghai Tech.). Our code and models are available online at https://github.com/SkiddieAhn/Paper-Making-Anomalies-More-Anomalous .

PaperPDFCode

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

Anomaly DetectionVideo Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection CUHK Avenue MAMA AUC 91.2% #15 of 35 Archive leaderboard report
Anomaly Detection ShanghaiTech MAMA AUC 76.5% #23 of 31 Archive leaderboard report
Anomaly Detection UCSD Ped2 MAMA AUC 98.2% #5 of 14 Archive leaderboard report
Video Anomaly Detection CUHK Avenue MAMA AUC 91.2% #4 of 7 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