Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting

Feng, Zhenhua, Kittler, Josef, Christmas, William, Huber, Patrik and Wu, X-J (2017) Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), 2017-07-21 - 2017-07-26, Honolulu, Hawaii.

Preview	Text 2017_CVPR.pdf - Accepted version Manuscript Available under License : See the attached licence file. Download (3MB) | Preview
Preview	Text (licence) SRI_deposit_agreement.pdf Available under License : See the attached licence file. Download (33kB) | Preview

Abstract

We present a new Cascaded Shape Regression (CSR) architecture, namely Dynamic Attention-Controlled CSR (DAC-CSR), for robust facial landmark detection on unconstrained faces. Our DAC-CSR divides facial landmark detection into three cascaded sub-tasks: face bounding box refinement, general CSR and attention-controlled CSR. The first two stages refine initial face bounding boxes and output intermediate facial landmarks. Then, an online dynamic model selection method is used to choose appropriate domain-specific CSRs for further landmark refinement. The key innovation of our DAC-CSR is the fault-tolerant mechanism, using fuzzy set sample weighting, for attentioncontrolled domain-specific model training. Moreover, we advocate data augmentation with a simple but effective 2D profile face generator, and context-aware feature extraction for better facial feature representation. Experimental results obtained on challenging datasets demonstrate the merits of our DAC-CSR over the state-of-the-art methods.

Item Type:	Conference or Workshop Item (Conference Paper)
Subjects :	Electronic Engineering
Divisions :	Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :	Name Email ORCID Feng, Zhenhua z.feng@surrey.ac.uk Kittler, Josef J.Kittler@surrey.ac.uk Christmas, William W.Christmas@surrey.ac.uk Huber, Patrik p.huber@surrey.ac.uk Wu, X-J
Date :	9 November 2017
Funders :	EPSRC
DOI :	10.1109/CVPR.2017.392
Copyright Disclaimer :	© 2017 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.
Contributors :	Contribution Name Email ORCID IEEE,
Related URLs :	Organisation Publisher
Depositing User :	Symplectic Elements
Date Deposited :	26 Apr 2017 09:41
Last Modified :	11 Dec 2018 11:23
URI:	http://epubs.surrey.ac.uk/id/eprint/814031

Actions (login required)

View Item

Downloads