{"slug": "mgface-mask-gated-face-matching-via-conditional-similarity-routing", "title": "MGFace: Mask-Gated Face Matching via Conditional Similarity Routing", "summary": "Researchers proposed MGFace, a mask-gated face identification pipeline that conditionally routes similarity computation based on whether a query face is masked, achieving over 90% accuracy with ArcFace backbone on the LFW-Mask dataset while reducing query time by 20x compared to previous methods.", "body_md": "arXiv:2607.13187v1 Announce Type: new\nAbstract: 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 https://github.com/chequanghuy/MGFace.", "url": "https://wpnews.pro/news/mgface-mask-gated-face-matching-via-conditional-similarity-routing", "canonical_source": "https://arxiv.org/abs/2607.13187", "published_at": "2026-07-16 04:00:00+00:00", "updated_at": "2026-07-16 04:09:48.880032+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "artificial-intelligence"], "entities": ["MGFace", "FaceNet", "ArcFace", "LFW-Mask"], "alternates": {"html": "https://wpnews.pro/news/mgface-mask-gated-face-matching-via-conditional-similarity-routing", "markdown": "https://wpnews.pro/news/mgface-mask-gated-face-matching-via-conditional-similarity-routing.md", "text": "https://wpnews.pro/news/mgface-mask-gated-face-matching-via-conditional-similarity-routing.txt", "jsonld": "https://wpnews.pro/news/mgface-mask-gated-face-matching-via-conditional-similarity-routing.jsonld"}}