Adaptive Video Anomaly Detection by Attention-Based Relational Knowledge Distillation
Open Access
- 4 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 117170-117185
Abstract
Detecting anomaly patterns in videos is a challenging task due to complex scenes, huge diversity of anomalies, and fuzzy nature of the task. With advent of technology, tremendous size of visual data is being generated by video surveillance systems, which makes harder to search, analyze, and detect anomalies on video data by human operators. In this paper, we introduce three relational distillation approaches to handle both robust detection of anomalous events and gradual adaptation to different anomaly patterns in new videos while not forgetting anomaly patterns learned from the previous video data. In order to realize these concepts, we propose a unique attention mechanism with feature and relation based knowledge distillation methods. We adapted our knowledge distillation methods to two state-of-the-art models designed for anomaly detection task. Our extensive experiments on two public datasets show that the proposed distillation methods improve the performance while reducing catastrophic forgetting problem.Keywords
Funding Information
- Scientific and Technological Research Council of Türkiye (119E098)
- Hacettepe University Scientific Research Projects Coordination Department (FHD-2022-20044)
This publication has 48 references indexed in Scilit:
- An adaptive teacher–student learning algorithm with decomposed knowledge distillation for on-edge intelligenceEngineering Applications of Artificial Intelligence, 2022
- Teacher–student knowledge distillation based on decomposed deep feature representation for intelligent mobile applicationsExpert Systems with Applications, 2022
- Knowledge Distillation: A SurveyInternational Journal of Computer Vision, 2021
- A tucker decomposition based knowledge distillation for intelligent edge applicationsApplied Soft Computing, 2021
- Feature Normalized Knowledge Distillation for Image Classification2020
- CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection2020
- Not only Look, But Also Listen: Learning Multimodal Violence Detection Under Weak Supervision2020
- Video Anomaly Detection for Smart Surveillance2020
- Deep learning approaches for video-based anomalous activity detectionWorld Wide Web, 2018
- Abnormal Event Detection in Videos Using Spatiotemporal Autoencoder2017