Department of Mathematics
 Search | Help | Login | pdf version | printable version

Math @ Duke



Publications [#322679] of Guillermo Sapiro

Papers Published

  1. Huang, J; Qiu, Q; Calderbank, R; Sapiro, G, Geometry-aware deep transform, Proceedings of the Ieee International Conference on Computer Vision, vol. 2015 International Conference on Compute (February, 2015), pp. 4139-4147, IEEE, ISBN 9781467383912 [doi]
    (last updated on 2019/06/17)

    © 2015 IEEE. 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.
ph: 919.660.2800
fax: 919.660.2821

Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320