• Home
  • Search
  • Online Meta-learning for Multi-source and Semi-supervised Domain Adaptation
  • Open Access IconOpen Access
  • Cite Icon108
  • https://doi.org/10.1007/978-3-030-58517-4_23Copy DOI Icon

Online Meta-learning for Multi-source and Semi-supervised Domain Adaptation

  • Jan 1, 2020
  • Da Li +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

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 demonstrate 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.

Similar Papers
  • Research Article
  • Citations36

From unsupervised to semi-supervised adversarial domain adaptation in electroencephalography-based sleep staging

  • Jun 01, 2022
  • Journal of Neural Engineering
  • Elisabeth R M Heremans +5
  • Research Article
  • Citations33

Unsupervised and Semi-Supervised Robust Spherical Space Domain Adaptation.

  • Mar 01, 2024
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Xiang Gu +2
  • Conference Article
  • Citations14

Semi-supervised Domain Adaptation in Graph Transfer Learning

  • Aug 01, 2023
  • Ziyue Qiao +5
  • Research Article
  • Citations11

LMDT: A weakly-supervised large-margin-domain-transfer for handwritten digit recognition

  • Mar 22, 2016
  • Engineering Applications of Artificial Intelligence
  • Hamidreza Hosseinzadeh +1
  • Research Article
  • Citations1

IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation

  • Apr 28, 2025
  • ACM Transactions on Intelligent Systems and Technology
  • Shima Rashidi +9
  • Conference Article
  • Citations51

Cross-Dataset Adaptation for Visual Question Answering

  • Jun 01, 2018
  • Fei Sha +2
  • Video Transcripts

Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training

  • Dec 29, 2020
  • Underline Science Inc.
  • Yoonhyung Kim
  • Conference Article
  • Citations10

Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training

  • Jan 10, 2021
  • Yoonhyung Kim +1
  • Research Article
  • Citations35

Domain Adaptation for Structured Regression

  • Dec 13, 2013
  • International Journal of Computer Vision
  • Makoto Yamada +2
  • Book Chapter
  • Citations110

Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation

  • Jan 01, 2020
  • Taekyung Kim +1
  • Research Article
  • Citations9

Scatter Matrix Based Domain Adaptation for Bi-Temporal Polarimetric SAR Images

  • Feb 17, 2020
  • Remote Sensing
  • Weidong Sun +6
  • Book Chapter
  • Citations43

M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning

  • Jan 01, 2020
  • Issam H Laradji +1
  • Research Article

Unmarked satellite pose estimation with semi-supervised domain adaptation and information augmentation

  • Sep 03, 2025
  • Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
  • Shengpeng Chen +4
  • Conference Article
  • Citations1

Semi-supervised domain adaptation via convolutional neural network

  • Sep 01, 2017
  • Pengcheng Liu +4
  • Research Article
  • Citations2

Multi-source semi-supervised condition constrained domain adaptation for process fault classification

  • Feb 28, 2025
  • Engineering Research Express
  • Xiaoping Guo +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.