Injecting Sparsity in Anomaly Detection for Efficient Inference

Bokyeung Lee, Hanseok Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Anomaly detection in the video is a challenging problem in computer vision tasks. Deep networks recently have been successfully applied and achieved competitive performance in anomaly detection. Modern deep networks employ many modules which extract important features. The anomaly detection approaches just developed network architecture and inserted additional networks to improve performance, however, these methods generally require a tremendous amount of computational load and training parameters. Because of limitations in the real world such as field equipment, mobile system, etc., reducing the number of trainable parameters and model capacity is an important issue in anomaly detection. Moreover, the method, which improves the performance of the anomaly detection algorithm, should be developed without additional trainable parameters. In this paper, we propose a sparsity injecting module which reinforces the feature representation of the existing model and presents the abnormality score function using sparsity. In experimental results, our sparsity injecting module improves the performance of state-of-the-art methods without additional trainable parameters.

Original languageEnglish
Title of host publicationAVSS 2021 - 17th IEEE International Conference on Advanced Video and Signal-Based Surveillance
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665433969
DOIs
Publication statusPublished - 2021
Event17th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2021 - Virtual, Online, United States
Duration: 2021 Nov 162021 Nov 19

Publication series

NameAVSS 2021 - 17th IEEE International Conference on Advanced Video and Signal-Based Surveillance

Conference

Conference17th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2021
Country/TerritoryUnited States
CityVirtual, Online
Period21/11/1621/11/19

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Media Technology

Fingerprint

Dive into the research topics of 'Injecting Sparsity in Anomaly Detection for Efficient Inference'. Together they form a unique fingerprint.

Cite this