EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced Face Recognition With Residual Networks and Dilated Contextual Transformer Attention

Randa Nachet, Javier Garrigós, Tarik Boudghene Stambouli

IET Biometrics · 2026-01 · 2026 (1)

DOI: 10.1049/bme2/7309163 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Biometrics, online erschienen am 03.04.2026. Verfasst von Randa Nachet und 2 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad Politécnica de Cartagena.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Face recognition in unconstrained environments remains a challenging problem due to significant variations in facial appearance. In this article, a systematic investigation is conducted into the effectiveness of integrating attention mechanisms within a ResNet34 backbone. ResNet34 is adopted as a compact backbone compared to commonly used deeper ResNet variants, offering a good balance between representational capacity and computational cost. Specifically, three variants are examined: self‐attention (SA), contextual transformer (CoT) attention, and the proposed dilated CoT (DCoT) attention. The primary contribution of this study is the demonstration that DCoT, by enlarging the receptive field without substantially increasing the number of parameters, constitutes a more suitable architectural choice for this backbone. This integration enables the network to capture broader contextual information and attend more effectively to discriminative facial features. The proposed models are trained on the CASIA‐WebFace dataset and evaluated on standard benchmarks, including labled faces in the wild (LFW), CPLFW, and AgeDB_30. Extensive experiments show that the DCoT‐enhanced model achieves consistent improvements over the baseline and other attention variants. Notably, the best‐performing model attains an accuracy of 99.60% on the LFW dataset. These findings provide meaningful insights into the interaction between attention mechanisms and convolutional architectures, illustrating the efficacy of the proposed approach for face recognition in unconstrained, real‐world conditions, while using a moderately sized backbone that balances capacity and parameter count.

Förderung

  • Universidad Politécnica de Cartagena

Zitieren

APA

Nachet, R., Garrigós, J., & Stambouli, T. B. (2026). Enhanced Face Recognition With Residual Networks and Dilated Contextual Transformer Attention. IET Biometrics, 2026(1). https://doi.org/10.1049/bme2/7309163

Vancouver

Nachet R, Garrigós J, Stambouli TB. Enhanced Face Recognition With Residual Networks and Dilated Contextual Transformer Attention. IET Biometrics. 2026;2026(1). doi:10.1049/bme2/7309163

BibTeX
@article{Nachet2026,
  author = {Nachet, Randa and Garrigós, Javier and Stambouli, Tarik Boudghene},
  title = {Enhanced Face Recognition With Residual Networks and Dilated Contextual Transformer Attention},
  journal = {IET Biometrics},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1049/bme2/7309163}
}
Kostenlos starten →