Papers › VADMamba: Exploring State Space Models for Fast Video Anomaly Detection

VADMamba: Exploring State Space Models for Fast Video Anomaly Detection

27 Mar 2025arXiv:2503.21169archive 2025-07-28

Jiahao Lyu, Minghua Zhao, Jing Hu, Xuewen Huang, Yifei Chen, Shuangli Du

Video anomaly detection (VAD) methods are mostly CNN-based or Transformer-based, achieving impressive results, but the focus on detection accuracy often comes at the expense of inference speed. The emergence of state space models in computer vision, exemplified by the Mamba model, demonstrates improved computational efficiency through selective scans and showcases the great potential for long-range modeling. Our study pioneers the application of Mamba to VAD, dubbed VADMamba, which is based on multi-task learning for frame prediction and optical flow reconstruction. Specifically, we propose the VQ-Mamba Unet (VQ-MaU) framework, which incorporates a Vector Quantization (VQ) layer and Mamba-based Non-negative Visual State Space (NVSS) block. Furthermore, two individual VQ-MaU networks separately predict frames and reconstruct corresponding optical flows, further boosting accuracy through a clip-level fusion evaluation strategy. Experimental results validate the efficacy of the proposed VADMamba across three benchmark datasets, demonstrating superior performance in inference speed compared to previous work. Code is available at https://github.com/jLooo/VADMamba.

PaperPDFCode

Code

jLooo/VADMamba officialmentioned in paperpytorch report

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 DetectionComputational EfficiencyLong-range modelingMambaMulti-Task LearningOptical Flow EstimationQuantizationState Space ModelsVideo Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Anomaly Detection CUHK Avenue VADMamba AUC 91.5% #3 of 7 Archive leaderboard report
Video Anomaly Detection ShanghaiTech Campus VADMamba AUC 77.0% #3 of 4 Archive leaderboard report
Video Anomaly Detection UCSD Ped2 VADMamba AUC 98.5% #2 of 3 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

FocusMambaSPEED

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