Skip to main content

Discriminative robust transformation learning

Publication ,  Conference
Huang, J; Qiu, Q; Sapiro, G; Calderbank, R
Published in: Advances in Neural Information Processing Systems
January 1, 2015

This paper proposes a framework for learning features that are robust to data variation, which is particularly important when only a limited number of training samples are available. The framework makes it possible to tradeoff the discriminative value of learned features against the generalization error of the learning algorithm. Robustness is achieved by encouraging the transform that maps data to features to be a local isometry. This geometric property is shown to improve (K, ∈)-robustness, thereby providing theoretical justification for reductions in generalization error observed in experiments. The proposed optimization framework is used to train standard learning algorithms such as deep neural networks. Experimental results obtained on benchmark datasets, such as labeled faces in the wild, demonstrate the value of being able to balance discrimination and robustness.

Duke Scholars

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2015

Volume

2015-January

Start / End Page

1333 / 1341

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Huang, J., Qiu, Q., Sapiro, G., & Calderbank, R. (2015). Discriminative robust transformation learning. In Advances in Neural Information Processing Systems (Vol. 2015-January, pp. 1333–1341).
Huang, J., Q. Qiu, G. Sapiro, and R. Calderbank. “Discriminative robust transformation learning.” In Advances in Neural Information Processing Systems, 2015-January:1333–41, 2015.
Huang J, Qiu Q, Sapiro G, Calderbank R. Discriminative robust transformation learning. In: Advances in Neural Information Processing Systems. 2015. p. 1333–41.
Huang, J., et al. “Discriminative robust transformation learning.” Advances in Neural Information Processing Systems, vol. 2015-January, 2015, pp. 1333–41.
Huang J, Qiu Q, Sapiro G, Calderbank R. Discriminative robust transformation learning. Advances in Neural Information Processing Systems. 2015. p. 1333–1341.

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2015

Volume

2015-January

Start / End Page

1333 / 1341

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology