Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces MGFace, a novel face identification pipeline that enhances accuracy for partially occluded faces by predicting mask status and adapting similarity computation accordingly. By employing global embedding matching for unmasked queries and activating mask-aware patch-level re-ranking solely for masked queries, MGFace significantly reduces computational overhead while maintaining high identification accuracy. Experimental results on the extended LFW-Mask dataset reveal that MGFace achieves over 80% accuracy with FaceNet and over 90% with ArcFace, outperforming previous methods while decreasing query time by approximately 20 times.
MGFace achieves over 90% identification accuracy for masked faces while slashing query time by 20x compared to traditional methods.
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.