Masked Face Recognition under Different Backbones
This work addresses the challenge of masked face recognition for civil aviation security, but it is incremental as it focuses on comparative evaluation of existing models.
The paper evaluated various backbone networks for face recognition, finding that r100 series models achieved over 98% accuracy in standard tests, while r100_mask_v2 led with 90.07% accuracy in masked tests, with ViT-Small/Tiny showing strong masked performance gains.
Erratum to the paper (Zhang et al., 2025): corrections to Table IV and the data in Page 3, Section A. In the post-pandemic era, a high proportion of civil aviation passengers wear masks during security checks, posing significant challenges to traditional face recognition models. The backbone network serves as the core component of face recognition models. In standard tests, r100 series models excelled (98%+ accuracy at 0.01% FAR in face comparison, high top1/top5 in search). r50 ranked second, r34_mask_v1 lagged. In masked tests, r100_mask_v2 led (90.07% accuracy), r50_mask_v3 performed best among r50 but trailed r100. Vit-Small/Tiny showed strong masked performance with gains in effectiveness. Through extensive comparative experiments, this paper conducts a comprehensive evaluation of several core backbone networks, aiming to reveal the impacts of different models on face recognition with and without masks, and provide specific deployment recommendations.