Ring-Regularized Cosine Similarity Learning for Fine-Grained Face Verification

摘要

Face verification aims to determine whether a pair of face images belong to the same person. Different from the traditional face verification, the negative sample pairs in fine-grained face verification are com-posed of similar face images, e.g., facial images of twins, which makes it still very challenging. In this paper, we investigate the fine-grained face verification problem via metric learning techniques, and pro -pose a ring-regularized cosine similarity learning (RRCSL) method to distinguish the negative face pairs. The proposed RRCSL method seeks a linear transformation to enlarge the cosine similarity of intra-class and reduce the cosine similarity of inter-class as much as possible, and adaptively learns the norm of samples to the scaled circle by exploiting the ring regularization term simultaneously. Experimental re-sults on three face datasets demonstrate the effectiveness of RRCSL for fine-grained face verification. (c) 2021 Elsevier B.V. All rights reserved.