Uncertainty-guided continual learning in Bayesian neural networks – Extended abstract

Sayna Ebrahimi, Mohamed Elhoseiny, Trevor Darrell, Marcus Rohrbach

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

8 Scopus citations

Abstract

Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based continual learning algorithms need an external representation and extra computation to measure the parameters’ importance. In contrast, we propose Bayesian Continual Learning (BCL), where the learning rate adapts according to the uncertainty defined in the probability distribution of the weights in networks. We evaluate our BCL approach extensively on diverse object classification datasets with short and long sequences of tasks and report superior or on-par performance compared to existing approaches. Additionally we show that our model can be task-independent at test time, i.e. it does not presume knowledge of which task a sample belongs to.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
PublisherIEEE Computer Society
Pages75-78
Number of pages4
ISBN (Electronic)9781728125060
StatePublished - Jun 2019
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 - Long Beach, United States
Duration: Jun 16 2019Jun 20 2019

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2019-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Country/TerritoryUnited States
CityLong Beach
Period06/16/1906/20/19

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Uncertainty-guided continual learning in Bayesian neural networks – Extended abstract'. Together they form a unique fingerprint.

Cite this