MGFace: Mask-Gated Face Matching via Conditional Similarity Routing
Quick Answer
MGFace introduces a mask-gated face identification pipeline that enhances accuracy for masked faces, achieving over 80% accuracy with FaceNet and over 90% with ArcFace.
Quick Take
MGFace introduces a mask-gated face identification pipeline that enhances accuracy for masked faces, achieving over 80% accuracy with FaceNet and over 90% with ArcFace. This method reduces query time by approximately 20x compared to traditional EMD-based re-ranking, making it efficient for large-scale retrieval. The approach focuses on upper-face regions, optimizing performance while minimizing computational costs.
Key Points
- MGFace predicts mask status to optimize similarity computation.
- Achieves over 80% accuracy with FaceNet and over 90% with ArcFace.
- Reduces query time by approximately 20x compared to EMD-based methods.
- Focuses on upper-face regions to enhance identification reliability.
- Source code is publicly available for further research.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Face identification has achieved remarkable performance under normal conditions. Yet, its accuracy often degrades significantly when query faces are partially occluded, especially by facial masks. Existing re-ranking approaches improve robustness by exploiting patch-level similarities. Still, they often rely on costly, fine-grained matching mechanisms, which limit their efficiency in large-scale retrieval scenarios. In this paper, we propose MGFace, a mask-gated face identification pipeline that predicts the mask status of a query face and conditionally routes the similarity computation accordingly. Specifically, MGFace distinguishes between masked and unmasked queries, applies global embedding matching to unmasked queries, and activates mask-aware patch-level re-ranking only for masked queries. This design focuses on reliable upper-face regions while avoiding unnecessary fine-grained computation. Experiments on the extended LFW-Mask dataset show that MGFace achieves over 80% identification accuracy with the FaceNet backbone and over 90% with the ArcFace backbone. Compared with a previous EMD-based re-ranking method, MGFace achieves better identification performance while reducing query time by approximately 20x. These results demonstrate the effectiveness of MGFace in improving masked-face identification accuracy with low computational overhead. The source code is available at this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2607.13187 [cs.CV] |
| (or arXiv:2607.13187v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.13187 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Quang Huy Che [view email]
[v1]
Tue, 14 Jul 2026 18:39:18 UTC (734 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.