KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition

TL;DR

KappaFace introduces an adaptive additive angular margin loss that dynamically adjusts to class difficulty and imbalance, significantly improving deep face recognition performance on benchmark datasets.

Contribution

The paper proposes KappaFace, a novel adaptive loss function that considers class imbalance and difficulty, enhancing deep face recognition accuracy.

Findings

Outperforms state-of-the-art methods on facial benchmarks

Effectively handles class imbalance in face recognition

Improves generalization by adaptive margin modulation

Abstract

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.