Angular Learning: Toward Discriminative Embedded Features

TL;DR

This paper introduces an angular loss method that enhances feature discriminability by promoting intra-class compactness and inter-class separability, while reducing overfitting and hyperparameter tuning.

Contribution

The proposed angular loss maximizes angular gradients to improve discriminative features with only one hyperparameter, outperforming existing margin-based softmax losses.

Findings

Improves face recognition accuracy

Enhances intra-class compactness and inter-class separability

Reduces overfitting and hyperparameter sensitivity

Abstract

The margin-based softmax loss functions greatly enhance intra-class compactness and perform well on the tasks of face recognition and object classification. Outperformance, however, depends on the careful hyperparameter selection. Moreover, the hard angle restriction also increases the risk of overfitting. In this paper, angular loss suggested by maximizing the angular gradient to promote intra-class compactness avoids overfitting. Besides, our method has only one adjustable constant for intra-class compactness control. We define three metrics to measure inter-class separability and intra-class compactness. In experiments, we test our method, as well as other methods, on many well-known datasets. Experimental results reveal that our method has the superiority of accuracy improvement, discriminative information, and time-consumption.