Skip to main content

Geometry-aware deep transform

Publication ,  Conference
Huang, J; Qiu, Q; Calderbank, R; Sapiro, G
Published in: Proceedings of the IEEE International Conference on Computer Vision
February 17, 2015

Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets. The success of these deep learning methods mostly relies on an enormous volume of labeled training samples to learn a huge number of parameters in a network, therefore, understanding the generalization ability of a learned deep network cannot be overlooked, especially when restricted to a small training set, which is the case for many applications. In this paper, we propose a novel deep learning objective formulation that unifies both the classification and metric learning criteria. We then introduce a geometry-aware deep transform to enable a non-linear discriminative and robust feature transform, which shows competitive performance on small training sets for both synthetic and real-world data. We further support the proposed framework with a formal (K)-robustness analysis.

Duke Scholars

Published In

Proceedings of the IEEE International Conference on Computer Vision

DOI

ISSN

1550-5499

ISBN

9781467383912

Publication Date

February 17, 2015

Volume

2015 International Conference on Computer Vision, ICCV 2015

Start / End Page

4139 / 4147
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Huang, J., Qiu, Q., Calderbank, R., & Sapiro, G. (2015). Geometry-aware deep transform. In Proceedings of the IEEE International Conference on Computer Vision (Vol. 2015 International Conference on Computer Vision, ICCV 2015, pp. 4139–4147). https://doi.org/10.1109/ICCV.2015.471
Huang, J., Q. Qiu, R. Calderbank, and G. Sapiro. “Geometry-aware deep transform.” In Proceedings of the IEEE International Conference on Computer Vision, 2015 International Conference on Computer Vision, ICCV 2015:4139–47, 2015. https://doi.org/10.1109/ICCV.2015.471.
Huang J, Qiu Q, Calderbank R, Sapiro G. Geometry-aware deep transform. In: Proceedings of the IEEE International Conference on Computer Vision. 2015. p. 4139–47.
Huang, J., et al. “Geometry-aware deep transform.” Proceedings of the IEEE International Conference on Computer Vision, vol. 2015 International Conference on Computer Vision, ICCV 2015, 2015, pp. 4139–47. Scopus, doi:10.1109/ICCV.2015.471.
Huang J, Qiu Q, Calderbank R, Sapiro G. Geometry-aware deep transform. Proceedings of the IEEE International Conference on Computer Vision. 2015. p. 4139–4147.

Published In

Proceedings of the IEEE International Conference on Computer Vision

DOI

ISSN

1550-5499

ISBN

9781467383912

Publication Date

February 17, 2015

Volume

2015 International Conference on Computer Vision, ICCV 2015

Start / End Page

4139 / 4147