Task-discriminative domain alignment for unsupervised domain adaptation

Behnam Gholami, Pritish Sahu, Minyoung Kim, Vladimir Pavlovic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Domain Adaptation (DA), the process of effectively adapting task models learned on one domain, the source, to other related but distinct domains, the targets, with no or minimal retraining, is typically accomplished using the process of source-to-target manifold alignment. However, this process often leads to unsatisfactory adaptation performance, in part because it ignores the task-specific structure of the data. In this paper, we improve the performance of DA by introducing a discriminative discrepancy measure which takes advantage of auxiliary information available in the source and the target domains to better align the source and target distributions. Specifically, we leverage the cohesive clustering structure within individual data manifolds, associated with different tasks, to improve the alignment. This structure is explicit in the source, where the task labels are available, but is implicit in the target, making the problem challenging. We address the challenge by devising a deep DA framework, which combines a new task-driven domain alignment discriminator with domain regularizers that en-courage the shared features as task-specific and domain invariant, and prompt the task model to be data structure preserving, guiding its decision boundaries through the low density data regions. We validate our framework on standard benchmarks, including Digits (MNIST, USPS, SVHN, MNIST-M), PACS, and VisDA. Our results show that our proposal model consistently outperforms the state-of-the-art in unsupervised domain adaptation.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1327-1336
Number of pages10
ISBN (Electronic)9781728150239
DOIs
StatePublished - Oct 2019
Event17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
Duration: Oct 27 2019Oct 28 2019

Publication series

NameProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
Country/TerritoryKorea, Republic of
CitySeoul
Period10/27/1910/28/19

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Keywords

  • Adversarial methods
  • Domain adaptation
  • Stochastic embedding

Fingerprint

Dive into the research topics of 'Task-discriminative domain alignment for unsupervised domain adaptation'. Together they form a unique fingerprint.

Cite this