Not all domains are equally complex: Adaptive multi-domain learning

Ali Senhaji, Jenni Raitoharju, Moncef Gabbouj, Alexandros Iosifidis

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

Abstract

Deep learning approaches are highly specialized and require training separate models for different tasks. Multi-domain learning looks at ways to learn a multitude of different tasks, each coming from a different domain, at once. The most common approach in multi-domain learning is to form a domain agnostic model, the parameters of which are shared among all domains, and learn a small number of extra domain-specific parameters for each individual new domain. However, different domains come with different levels of difficulty; parameterizing the models of all domains using an augmented version of the domain agnostic model leads to unnecessarily inefficient solutions, especially for easy to solve tasks. We propose an adaptive parameterization approach to deep neural networks for multidomain learning. The proposed approach performs on par with the original approach while reducing by far the number of parameters, leading to efficient multi-domain learning solutions.

Original languageEnglish
Title of host publicationProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
PublisherIEEE
Pages8663-8670
Number of pages8
ISBN (Electronic)978-1-7281-8808-9
DOIs
Publication statusPublished - 2021
Publication typeA4 Article in a conference publication
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

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Not all domains are equally complex: Adaptive multi-domain learning'. Together they form a unique fingerprint.

Cite this