Research

Co-regularized Alignment for Unsupervised Domain Adaptation

Transfer Learning

Authors

Published on

11/13/2018

Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a target domain whose distribution differs from the training data distribution, referred as the source domain. It can be expensive or even infeasible to obtain required amount of labeled data in all possible domains. Unsupervised domain adaptation sets out to address this problem, aiming to learn a good predictive model for the target domain using labeled examples from the source domain but only unlabeled examples from the target domain. Domain alignment approaches this problem by matching the source and target feature distributions, and has been used as a key component in many state-of-the-art domain adaptation methods. However, matching the marginal feature distributions does not guarantee that the corresponding class conditional distributions will be aligned across the two domains. We propose co-regularized domain alignment for unsupervised domain adaptation, which constructs multiple diverse feature spaces and aligns source and target distributions in each of them individually, while encouraging that alignments agree with each other with regard to the class predictions on the unlabeled target examples. The proposed method is generic and can be used to improve any domain adaptation method which uses domain alignment. We instantiate it in the context of a recent state-of-the-art method and observe that it provides significant performance improvements on several domain adaptation benchmarks.

Please cite our work using the BibTeX below.

@article{DBLP:journals/corr/abs-1811-05443,
  author    = {Abhishek Kumar and
               Prasanna Sattigeri and
               Kahini Wadhawan and
               Leonid Karlinsky and
               Rog{\'{e}}rio Schmidt Feris and
               William T. Freeman and
               Gregory W. Wornell},
  title     = {Co-regularized Alignment for Unsupervised Domain Adaptation},
  journal   = {CoRR},
  volume    = {abs/1811.05443},
  year      = {2018},
  url       = {http://arxiv.org/abs/1811.05443},
  archivePrefix = {arXiv},
  eprint    = {1811.05443},
  timestamp = {Mon, 26 Nov 2018 07:38:20 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1811-05443.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Close Modal