Skip to main content

A dictionary approach to domain-invariant learning in deep networks

Publication ,  Journal Article
Wang, Z; Cheng, X; Sapiro, G; Qiu, Q
Published in: Advances in Neural Information Processing Systems
January 1, 2020

In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN). By exploiting the observation that a convolutional filter can be well approximated as a linear combination of a small set of dictionary atoms, we show for the first time, both empirically and theoretically, that domain shifts can be effectively handled by decomposing a convolutional layer into a domain-specific atom layer and a domain-shared coefficient layer, while both remain convolutional. An input channel will now first convolve spatially only with each respective domain-specific dictionary atom to “absorb" domain variations, and then output channels are linearly combined using common decomposition coefficients trained to promote shared semantics across domains. We use toy examples, rigorous analysis, and real-world examples with diverse datasets and architectures, to show the proposed plug-in framework’s effectiveness in cross and joint domain performance and domain adaptation. With the proposed architecture, we need only a small set of dictionary atoms to model each additional domain, which brings a negligible amount of additional parameters, typically a few hundred.

Duke Scholars

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2020

Volume

2020-December

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Wang, Z., Cheng, X., Sapiro, G., & Qiu, Q. (2020). A dictionary approach to domain-invariant learning in deep networks. In Advances in Neural Information Processing Systems (Vol. 2020-December).
Wang, Z., X. Cheng, G. Sapiro, and Q. Qiu. “A dictionary approach to domain-invariant learning in deep networks.” In Advances in Neural Information Processing Systems, Vol. 2020-December, 2020.
Wang Z, Cheng X, Sapiro G, Qiu Q. A dictionary approach to domain-invariant learning in deep networks. In: Advances in Neural Information Processing Systems. 2020.
Wang, Z., et al. “A dictionary approach to domain-invariant learning in deep networks.” Advances in Neural Information Processing Systems, vol. 2020-December, 2020.
Wang Z, Cheng X, Sapiro G, Qiu Q. A dictionary approach to domain-invariant learning in deep networks. Advances in Neural Information Processing Systems. 2020.

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2020

Volume

2020-December

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology