Cross-Domain Graph Convolutions for Adversarial Unsupervised Domain Adaptation
- 15 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34 (8) , 3847-3858
Abstract
Unsupervised domain adaptation (UDA) has attracted increasing attention in recent years, which adapts classifiers to an unlabeled target domain by exploiting a labeled source domain. To reduce the discrepancy between source and target domains, adversarial learning methods are typically selected to seek domain-invariant representations by confusing the domain discriminator. However, classifiers may not be well adapted to such a domain-invariant representation space, as the sample- and class-level data structures could be distorted during adversarial learning. In this article, we propose a novel transferable feature learning approach on graphs (TFLG) for unsupervised adversarial domain adaptation (DA), which jointly incorporates sample- and class-level structure information across two domains. TFLG first constructs graphs for minibatch samples and identifies the classwise correspondence across domains. A novel cross-domain graph convolutional operation is designed to jointly align the sample- and class-level structures in two domains. Moreover, a memory bank is designed to further exploit the class-level information. Extensive experiments on benchmark datasets demonstrate the effectiveness of our approach compared to the state-of-the-art UDA methods.Keywords
Funding Information
- U.S. Army Research Office Award (W911NF-21-1-0109)
This publication has 44 references indexed in Scilit:
- Unsupervised transfer learning via Low-Rank Coding for image clustering2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Visual Domain Adaptation: A survey of recent advancesIEEE Signal Processing Magazine, 2015
- Domain Adaptation on the Statistical Manifold2014
- Continuous Manifold Based Adaptation for Evolving Visual Domains2014
- Unsupervised Domain Adaptation by Domain Invariant Projection2013
- Adapting Visual Category Models to New Domains2010
- A theory of learning from different domainsMachine Learning, 2009
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Improving predictive inference under covariate shift by weighting the log-likelihood functionJournal of Statistical Planning and Inference, 2000