Masked Face Recognition under Different Backbones

TL;DR

This paper evaluates how different backbone networks affect face recognition accuracy in masked and unmasked scenarios, providing insights and recommendations for deployment in security contexts.

Contribution

It offers a comprehensive comparison of various backbone models' performance on masked face recognition, highlighting the effectiveness of certain architectures like r100_mask_v2 and Vit-Small/Tiny.

Findings

r100_mask_v2 achieves 90.07% accuracy on masked face recognition

Vit-Small/Tiny models show strong masked face recognition performance

Different backbones significantly impact recognition accuracy under masked conditions

Abstract

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.