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

Math @ Duke



Publications [#335964] of Guillermo Sapiro

Papers Published

  1. Qiu, Q; Hashemi, J; Sapiro, G, Intelligent synthesis driven model calibration: framework and face recognition application, Proceedings 2017 Ieee International Conference on Computer Vision Workshops, Iccvw 2017, vol. 2018-January (January, 2018), pp. 2564-2572, IEEE, ISBN 9781538610343 [doi]
    (last updated on 2019/06/16)

    © 2017 IEEE. Deep Neural Networks (DNNs) that achieve state-of-the-art results are still prone to suffer performance degradation when deployed in many real-world scenarios due to shifts between the training and deployment domains. Limited data from a given setting can be enriched through synthesis, then used to calibrate a pre-trained DNN to improve the performance in the setting. Most enrichment approaches try to generate as much data as possible; however, this blind approach is computationally expensive and can lead to generating redundant data. Contrary to this, we develop synthesis, here exemplified for faces, methods and propose information-driven approaches to exploit and optimally select face synthesis types both at training and testing. We show that our approaches, without re-designing a new DNN, lead to more efficient training and improved performance. We demonstrate the effectiveness of our approaches by calibrating a state-of-the-art DNN to two challenging face recognition datasets.
ph: 919.660.2800
fax: 919.660.2821

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