University of Oulu

Álvarez Casado, C., Bordallo López, M. (2019) Face alignment: improving the accuracy of fast models using domain-specific unlabelled data and a teacher–student scheme. Electronics Letters, 55 (11), 646-648. doi:10.1049/el.2019.0319

Face alignment : improving the accuracy of fast models using domain-specific unlabelled data and a teacher–student scheme

Saved in:
Author: Casado, Constantino Álvarez1; Bordallo López, Miguel2
Organizations: 1Visidon OY, Finland
2Center for Machine Vision and Signal Analysis, University of Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.3 MB)
Persistent link:
Language: English
Published: Institution of Engineering and Technology, 2019
Publish Date: 2019-09-05


Face alignment is a crucial step in multiple face analysis and recognition tasks. The current state-of-the-art is comprised by very slow methods based on deep learning that require computationally heavy inference and very fast methods based on cascades of regressors that lack the ability to cope with complicated cases or extreme poses. The authors show how collecting a small subset of unlabelled domain-specific data can improve the accuracy of fast-inference models utilising data annotated by a slower one and a teacher–student architecture. In the proposed solution, they annotate a small subset of facial images belonging to two challenging domains using a slow but more accurate model, and this data is used to incrementally train a fast one. Their results show that by adding as little as a 5% of challenging data, they can reduce the error rate in a specific domain up to 30% without losing any generalisation abilities. This training scheme has applicability in numerous computer vision and engineering problems where computational power and model size are constrained by the application and platform or real-time operation is a requirement.

see all

Series: Electronics letters
ISSN: 0013-5194
ISSN-E: 1350-911X
ISSN-L: 0013-5194
Volume: 55
Issue: 11
Pages: 646 - 648
DOI: 10.1049/el.2019.0319
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
Copyright information: © The Institution of Engineering and Technology. This paper is a postprint of a paper submitted to and accepted for publication in IET Electronics Letters and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at the IET Digital Library.