University of Oulu

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

Adaptive cascaded regression

Saved in:
Author: Antonakos, Epameinondas1,2; Snape, Patrick1,2; Trigeorgis, George1;
Organizations: 1Department of Computing, Imperial College London, U.K.
2Center for Machine Vision and Signal Analysis, University of Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2016
Publish Date: 2019-02-28


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.

see all

Series: IEEE International Conference on Image Processing
ISSN: 1522-4880
ISSN-E: 2381-8549
ISSN-L: 1522-4880
ISBN Print: 978-1-4673-9961-6
Pages: 1649 - 1653
DOI: 10.1109/ICIP.2016.7532638
Host publication: 2016 IEEE International Conference on Image Processing (ICIP)
Conference: IEEE international conference on image processing
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Funding: The work of E. Antonakos and P. Snape was funded by the European Community Horizon 2020 [H2020/2014-2020] under grant agreement no. 688520 (TeSLA). G. Trigeorgis was funded by a DTA from Imperial College London. The work of S. Zafeiriou was funded by the FiDiPro program of Tekes (project number: 1849/31/2015).
Copyright information: © 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.