KappaFace：用于深度人脸识别的自适应加性角度间隔损失
KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition
AI总结：
针对深度人脸识别中的类别不平衡问题，提出 KappaFace 自适应加性角度间隔损失，依据类别难度与集中度动态调节间隔，并在多个基准上超越现有方法。
摘要：
特征学习是一种被广泛用于大规模人脸识别的方法。近来，大间隔 softmax 损失方法已在深度人脸识别上展现出显著提升。这些方法提出固定的正间隔，以增强类内紧凑性和类间差异性。然而，大多数已提出的方法没有考虑类别不平衡问题，而这在实践中是开发深度人脸识别模型的一项主要挑战。我们假设该问题会显著影响深度人脸模型的泛化能力。受这一观察启发，我们提出一种名为 KappaFace 的新型自适应策略，根据类别难度和不平衡程度调节相对重要性。在 von Mises-Fisher 分布的支持下，我们提出的 KappaFace 损失能够针对困难学习类别或低集中度类别加大间隔幅度，同时对相反类别放宽间隔。在常用人脸基准上进行的实验表明，我们提出的方法取得了优于当前最先进方法的性能。
英文摘要：
Feature learning is a widely used method employed for large-scale face recognition. Recently, large-margin softmax loss methods have demonstrated significant enhancements on deep face recognition. These methods propose fixed positive margins in order to enforce intra-class compactness and inter-class diversity. However, the majority of the proposed methods do not consider the class imbalance issue, which is a major challenge in practice for developing deep face recognition models. We hypothesize that it significantly affects the generalization ability of the deep face models. Inspired by this observation, we introduce a novel adaptive strategy, called KappaFace, to modulate the relative importance based on class difficultness and imbalance. With the support of the von Mises-Fisher distribution, our proposed KappaFace loss can intensify the margin's magnitude for hard learning or low concentration classes while relaxing it for counter classes. Experiments conducted on popular facial benchmarks demonstrate that our proposed method achieves superior performance to the state-of-the-art.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
