Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

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

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

For access to this article, please select a purchase option:

Buy article PDF
$19.95
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
Electronics Letters — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

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.

References

    1. 1)
      • 14. Bucilua, C., Caruana, R., Niculescu-Mizil, A.: ‘Model compression’. ACM Int. Conf. on Knowledge Discovery and Data Mining, Philadelphia, PA, USA, August 2006.
    2. 2)
    3. 3)
      • 10. Kowalski, M., Naruniec, J., Trzcinski, T.: ‘Deep alignment network: a convolutional neural network for robust face alignment’. Proc. Int. Conf. on Computer Vision & Pattern Recognition (CVPRW), Honolulu, HI, USA, July 2017.
    4. 4)
    5. 5)
      • 6. Bordallo López, J., Thevenot, M., Hadid, A.: ‘A survey on computer vision for assistive medical diagnosis from faces’, J. Biomed. Health Inf., 2017, pp. 114.
    6. 6)
      • 2. Komulainen, J., Boulkenafet, Z., Akhtar, Z.: ‘Review of face presentation attack detection competitions’, in Marcel, S., Nixon, M.S., Li, S.Z. (Eds.): ‘Handbook of Biometric Anti-Spoofing: Presentation Attack Detection’ (Springer Nature Switzerland AG, Cham, Switzerland, 2019), pp. 291317.
    7. 7)
      • 9. Shi, B., Bai, X., Liu, W., et al: ‘Face alignment with deep regression’, Trans. Neural Netw. Learn. Syst., 2018.
    8. 8)
    9. 9)
      • 11. Ren, S., Cao, X., Wei, Y., et al: ‘Face alignment at 3000 fps via regressing local binary features’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, OH, USA, June 2014, pp. 16851692.
    10. 10)
    11. 11)
    12. 12)
      • 5. Martinez, B., Valstar, M.F., Jiang, B., et al: ‘Automatic analysis of facial actions: a survey’, Trans Affective Comput., 2017, doi: 10.1109/TAFFC.2017.2731763.
    13. 13)
    14. 14)
      • 16. Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., et al: ‘A semi-automatic methodology for facial landmark annotation’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition Workshops, Portland, OR, USA, June 2013, pp. 896903.
    15. 15)
      • 12. Kazemi, V., Sullivan, J.: ‘One millisecond face alignment with an ensemble of regression trees’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, OH, USA, June 2014, pp. 18671874.
    16. 16)
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2019.0319
Loading

Related content

content/journals/10.1049/el.2019.0319
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address