Adaptive cascaded regression

Antonakos, Epameinondas; Snape, Patrick; Trigeorgis, George; Zafeiriou, Stefanos (2016-08-19)
 
Avaa tiedosto
Lataukset: 

URL:
https://doi.org/10.1109/ICIP.2016.7532638

Antonakos, Epameinondas
Snape, Patrick
Trigeorgis, George
Zafeiriou, Stefanos
Institute of Electrical and Electronics Engineers
19.08.2016

E. Antonakos, P. Snape, G. Trigeorgis and S. Zafeiriou, "Adaptive cascaded regression," 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, 2016, pp. 1649-1653. doi: 10.1109/ICIP.2016.7532638

https://rightsstatements.org/vocab/InC/1.0/
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
doi:https://doi.org/10.1109/ICIP.2016.7532638
Näytä kaikki kuvailutiedot
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe201902286522
Tiivistelmä

Abstract

The two predominant families of deformable models for the task of face alignment are: (i) discriminative cascaded regression models, and (ii) generative models optimised with Gauss-Newton. Although these approaches have been found to work well in practise, they each suffer from convergence issues. Cascaded regression has no theoretical guarantee of convergence to a local minimum and thus may fail to recover the fine details of the object. Gauss-Newton optimisation is not robust to initialisations that are far from the optimal solution. In this paper, we propose the first, to the best of our knowledge, attempt to combine the best of these two worlds under a unified model and report state-of-the-art performance on the most recent facial benchmark challenge.

Kokoelmat