paper-with-me

홈 › Papers

Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation

2022-11-28 · Florinel-Alin Croitoru, Nicolae-Catalin Ristea, Dana Dascalescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah

We propose a very fast frame-level model for anomaly detection in video, which learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models. To improve the fidelity of our student, we distill the low-resolution anomaly maps of the teachers by jointly applying standard and adversarial distillation, introducing an adversarial discriminator for each teacher to distinguish between target and generated anomaly maps. We conduct experiments on three benchmarks (Avenue, ShanghaiTech, UCSD Ped2), showing that our method is over 7 times faster than the fastest competing method, and between 28 and 62 times faster than object-centric models, while obtaining comparable results to recent methods. Our evaluation also indicates that our model achieves the best trade-off between speed and accuracy, due to its previously unheard-of speed of 1480 FPS. In addition, we carry out a comprehensive ablation study to justify our architectural design choices. Our code is freely available at: https://github.com/ristea/fast-aed.

📄 PDF Abstract BibTeX arXiv:2211.15597

Code (1)

ristea/fast-aed 공식 구현 pytorch

Tasks

Anomaly DetectionKnowledge DistillationVideo Anomaly Detection

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

AnimateDiff-Lightning: Cross-Model Diffusion Distillation

2024-03-19 · Shanchuan Lin, Xiao Yang

We present AnimateDiff-Lightning for lightning-fast video generation. Our model uses progressive adversarial diffusion distillation to achieve new state-of-the-art in few-step video generation. We discuss our modificatio…

modelVideo Generation

Adversarial Machine Learning Attacks Against Video Anomaly Detection Systems

2022-04-07 · Furkan Mumcu, Keval Doshi, Yasin Yilmaz

Anomaly detection in videos is an important computer vision problem with various applications including automated video surveillance. Although adversarial attacks on image understanding models have been heavily investiga…

Anomaly DetectionBIG-bench Machine LearningVideo Anomaly DetectionVideo Understanding

Reward Lightning: Fast Video Generation via Homologous Preference Distillation

2026-07-04 · Jiaxiang Cheng, Bing Ma, Xuhua Ren, Kai Yu 외 arxiv

Achieving simultaneous preference alignment and distillation acceleration in video diffusion models remains an open challenge. Existing methods optimize the two objectives over mismatched representation spaces, where imp…

Video Generation

LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos

2024-05-22 · Yujun Shi, Jun Hao Liew, Hanshu Yan, Vincent Y. F. Tan 외

Accuracy and speed are critical in image editing tasks. Pan et al. introduced a drag-based image editing framework that achieves pixel-level control using Generative Adversarial Networks (GANs). A flurry of subsequent st…

Predicting Next Local Appearance for Video Anomaly Detection

2021-06-10 · Pankaj Raj Roy, Guillaume-Alexandre Bilodeau, Lama Seoud

We present a local anomaly detection method in videos. As opposed to most existing methods that are computationally expensive and are not very generalizable across different video scenes, we propose an adversarial framew…

Anomaly DetectionObjectVideo Anomaly Detection