Show simple item record

dc.contributor.authorKumar, Abhishek
dc.contributor.authorWadhawan, Kahini
dc.contributor.authorFeris, Rogerio
dc.contributor.authorSattigeri, Prasanna
dc.contributor.authorKarlinsky, Leonid
dc.contributor.authorFreeman, William T.
dc.contributor.authorWornell, Gregory
dc.date.accessioned2020-04-21T14:50:34Z
dc.date.available2020-04-21T14:50:34Z
dc.date.issued2018-12
dc.identifier.urihttps://hdl.handle.net/1721.1/124757
dc.description.abstractDeep 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, Quebecen_US
dc.language.isoen
dc.relation.isversionofhttp://papers.nips.cc/paper/8146-co-regularized-alignment-for-unsupervised-domain-adaptationen_US
dc.rightsArticle 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.en_US
dc.sourceNeural Information Processing Systems (NIPS)en_US
dc.titleCo-regularized alignment for unsupervised domain adaptationen_US
dc.typeArticleen_US
dc.identifier.citationKumar, 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)en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.departmentMIT-IBM Watson AI Lab
dc.relation.journalAdvances in Neural Information Processing Systemsen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2019-05-28T12:41:02Z
dspace.date.submission2019-05-28T12:41:03Z
mit.journal.volume31en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record