Co-regularized alignment for unsupervised domain adaptation
Name
8146-co-regularized-alignment-for-unsupervised-domain-adaptation.pdf
Description
Published version
Size
603.25 KB
Format
Adobe PDF
Checksum (MD5)
6436c3391eb7c1579517b41ef62c380d
Author(s)
Kumar, Abhishek
Wadhawan, Kahini
Feris, Rogerio
Sattigeri, Prasanna
Karlinsky, Leonid
Freeman, William T.
Wornell, Gregory
Date Issued
December 2018
Journal
Advances in Neural Information Processing Systems
Citation
Kumar, Abhishek, et al., "Co-regularized alignment for unsupervised domain adaptation." Advances in Neural Information Processing Systems 31, edited by S. Bengio, et al. (San Diego, California: Neural Information Processing Systems Foundation, Inc., 2018): url http://papers.nips.cc/paper/8146-co-regularized-alignment-for-unsupervised-domain-adaptation ©2018 Author(s)
Version
Final published version
Abstract
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. ©2018 Presented as poster at the 2018 Conference on Neural Information Processing Systems (NeurIPS 2018), December 3-8, 2018, Montreal, Quebec
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
MIT-IBM Watson AI Lab
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
http://papers.nips.cc/paper/8146-co-regularized-alignment-for-unsupervised-domain-adaptation
