EUVIMEDEUVIMED entdecken
Crossref

Boosting Variational Inference With Margin Learning for Few-Shot Scene-Adaptive Anomaly Detection

Xin Huang, Yutao Hu, Xiaoyan Luo, Jungong Han, Baochang Zhang, Xianbin Cao

IEEE Transactions on Circuits and Systems for Video Technology · 2023-06 · 33 (6) · 2813-2825

DOI: 10.1109/tcsvt.2022.3227716 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-06. Verfasst von Xin Huang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: National Key Research and Development Program, Major Instrument Projects of NSFC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anomaly detection in surveillance videos aims to identify frames where abnormal events happen. Existing approaches assume that the training and testing videos are from the same scene, exhibiting poor generalization performance when encountering an unseen scene. In this paper, we propose a Variational Anomaly Detection Network (VADNet), which is characterized by its high scene-adaptation - it can identify abnormal events in a new scene only via referring to a few normal samples without fine-tuning. Our model embodies two major innovations. First, a novel Variational Normal Inference (VNI) module is proposed to formulate image reconstruction in a conditional variational auto-encoder (CVAE) framework, which learns a probabilistic decision model instead of a traditional deterministic one. Secondly, a Margin Learning Embedding (MLE) module is leveraged to boost the variational inference and aid in distinguishing normal events. We theoretically demonstrate that minimizing the triplet loss in MLE module facilitates maximizing the evidence lower bound (ELBO) of CVAE, which promotes the convergence of VNI. By incorporating variational inference with margin learning, VADNet becomes much more generative that is able to handle the uncertainty caused by the changed scene and limited reference data. Extensive experiments on several datasets demonstrate that the proposed VADNet can adapt to a new scene effectively without fine-tuning and achieve remarkable performance, which outperforms other methods significantly and establishes new state-of-the-art in the case of few-shot scene-adaptive anomaly detection. We believe our method is closer to real-world application due to its strong generalization ability. All codes are released in https://github.com/huangxx156/VADNet.

Förderung

  • National Key Research and Development Program
  • Major Instrument Projects of NSFC

Zitieren

APA

Huang, X., Hu, Y., Luo, X., Han, J., Zhang, B., & Cao, X. (2023). Boosting Variational Inference With Margin Learning for Few-Shot Scene-Adaptive Anomaly Detection. IEEE Transactions on Circuits and Systems for Video Technology, 33(6), 2813-2825. https://doi.org/10.1109/tcsvt.2022.3227716

Vancouver

Huang X, Hu Y, Luo X, Han J, Zhang B, Cao X. Boosting Variational Inference With Margin Learning for Few-Shot Scene-Adaptive Anomaly Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(6):2813-2825. doi:10.1109/tcsvt.2022.3227716

BibTeX
@article{Huang2023,
  author = {Huang, Xin and Hu, Yutao and Luo, Xiaoyan and Han, Jungong and Zhang, Baochang and Cao, Xianbin},
  title = {Boosting Variational Inference With Margin Learning for Few-Shot Scene-Adaptive Anomaly Detection},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {6},
  pages = {2813--2825},
  doi = {10.1109/tcsvt.2022.3227716}
}
Kostenlos starten →