RSAC: Regularized subspace approximation classifier for lightweight continuous learning

Chih Hsing Ho, Shang Ho Tsai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Continuous learning seeks to perform the learning on the data that arrives from time to time. While prior works have demonstrated several possible solutions, these approaches require excessive training time as well as memory usage. This is impractical for applications where time and storage are constrained, such as edge computing. In this work, a novel training algorithm, regularized subspace approximation classifier (RSAC), is proposed to achieve lightweight continuous learning. RSAC contains a feature reduction module and classifier module with regularization. Extensive experiments show that RSAC is more efficient than prior continuous learning works and outperforms these works on various experimental settings.

Original languageEnglish
Title of host publicationProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7985-7991
Number of pages7
ISBN (Electronic)9781728188089
DOIs
StatePublished - 2020
Event25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Milan, Italy
Duration: 10 Jan 202115 Jan 2021

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference25th International Conference on Pattern Recognition, ICPR 2020
Country/TerritoryItaly
CityVirtual, Milan
Period10/01/2115/01/21

Keywords

  • Continuous learning
  • Incremental batch learning
  • Streaming learning

Fingerprint

Dive into the research topics of 'RSAC: Regularized subspace approximation classifier for lightweight continuous learning'. Together they form a unique fingerprint.

Cite this