EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multitask Learning Strategy with Pseudo-Labeling: Face Recognition, Facial Landmark Detection, and Head Pose Estimation

Yongju Lee iD, Sungjun Jang iD, Han Byeol Bae iD, Taejae Jeon iD, Sangyoun Lee

Sensors · 2024

DOI: 10.3390/s24103212 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Yongju Lee und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Electronic Engineering, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul 03722, Republic of Korea. Hauptthemen laut MEDLINE: Face, Head, Automated Facial Recognition. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea (NRF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Most facial analysis methods perform well in standardized testing but not in real-world testing. The main reason is that training models cannot easily learn various human features and background noise, especially for facial landmark detection and head pose estimation tasks with limited and noisy training datasets. To alleviate the gap between standardized and real-world testing, we propose a pseudo-labeling technique using a face recognition dataset consisting of various people and background noise. The use of our pseudo-labeled training dataset can help to overcome the lack of diversity among the people in the dataset. Our integrated framework is constructed using complementary multitask learning methods to extract robust features for each task. Furthermore, introducing pseudo-labeling and multitask learning improves the face recognition performance by enabling the learning of pose-invariant features. Our method achieves state-of-the-art (SOTA) or near-SOTA performance on the AFLW2000-3D and BIWI datasets for facial landmark detection and head pose estimation, with competitive face verification performance on the IJB-C test dataset for face recognition. We demonstrate this through a novel testing methodology that categorizes cases as soft, medium, and hard based on the pose values of IJB-C. The proposed method achieves stable performance even when the dataset lacks diverse face identifications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FaceHeadAutomated Facial RecognitionHumansAlgorithmsMachine LearningFacial RecognitionDatabases, FactualImage Processing, Computer-Assisted

Stichwörter der Autor:innen

face recognitionfacial landmark detectionhead pose estimationmultitask learningpseudo-labeling

Autor:innen und Institutionen

  • School of Electrical and Electronic Engineering, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul 03722, Republic of Korea.
  • School of Computer Science and Engineering, Kunsan National University, 558 Daehak-ro, Gunsan 54150, Jeollabuk-do, Republic of Korea.
  • Taejae JeonMX Division, Samsung Electronics Co., Ltd., Suwon 16677, Gyeonggi-do, Republic of Korea.

ORCID-Profile: Yongju Lee, Sungjun Jang, Han Byeol Bae, Taejae Jeon

Förderung

  • National Research Foundation of Korea (NRF)

Zitieren

APA

Lee, Y., Jang, S., Bae, H. B., Jeon, T., & Lee, S. (2024). Multitask Learning Strategy with Pseudo-Labeling: Face Recognition, Facial Landmark Detection, and Head Pose Estimation. Sensors. https://doi.org/10.3390/s24103212

Vancouver

Lee Y, Jang S, Bae HB, Jeon T, Lee S. Multitask Learning Strategy with Pseudo-Labeling: Face Recognition, Facial Landmark Detection, and Head Pose Estimation. Sensors. 2024. doi:10.3390/s24103212

BibTeX
@article{Lee2024,
  author = {Lee, Yongju and Jang, Sungjun and Bae, Han Byeol and Jeon, Taejae and Lee, Sangyoun},
  title = {Multitask Learning Strategy with Pseudo-Labeling: Face Recognition, Facial Landmark Detection, and Head Pose Estimation},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24103212}
}
Kostenlos starten →