Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation

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


Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to address this problem through different ways to minimise the domain shift between source and target datasets. In this paper we take an orthogonal perspective and propose a framework to further enhance performance by meta-learning the initial conditions of existing DA algorithms. This is challenging compared to the more widely considered setting of few-shot meta-learning, due to the length of the computation graph involved. Therefore we propose an online shortest-path meta-learning framework that is both computationally tractable and practically effective for improving DA performance. We present variants for both multi-source unsupervised domain adaptation (MSDA), and semi-supervised domain adaptation (SSDA). Importantly, our approach is agnostic to the base adaptation algorithm, and can be applied to improve many techniques. Experimentally, we demon-strate improvements on classic (DANN) and recent (MCD and MME) techniques for MSDA and SSDA, and ultimately achieve state of the art results on several DA benchmarks including the largest scale DomainNet.
Original languageEnglish
Title of host publicationComputer Vision – ECCV 2020
Subtitle of host publication16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVI
PublisherSpringer, Cham
Number of pages22
ISBN (Electronic)978-3-030-58517-4
ISBN (Print)978-3-030-58516-7
Publication statusPublished - 10 Oct 2020
Event16th European Conference on Computer Vision - Virtual conference
Duration: 23 Aug 202028 Aug 2020

Publication series

NameLecture Notes in Computer Science
PublisherSpringer, Cham
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference16th European Conference on Computer Vision
Abbreviated titleECCV 2020
CityVirtual conference
Internet address


  • meta-learning
  • domain adaptation


Dive into the research topics of 'Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation'. Together they form a unique fingerprint.

Cite this