Support Vector Guided Softmax Loss for Face Recognition

TL;DR

This paper introduces SV-Softmax, a novel loss function for face recognition that combines the strengths of mining-based and margin-based approaches to enhance feature discrimination and reduce ambiguity.

Contribution

The paper proposes SV-Softmax, the first loss function to integrate mining-based and margin-based strategies for improved face recognition performance.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effectively emphasizes misclassified support vectors.

Enhances discriminative feature learning in face recognition.

Abstract

Face recognition has witnessed significant progresses due to the advances of deep convolutional neural networks (CNNs), the central challenge of which, is feature discrimination. To address it, one group tries to exploit mining-based strategies (\textit{e.g.}, hard example mining and focal loss) to focus on the informative examples. The other group devotes to designing margin-based loss functions (\textit{e.g.}, angular, additive and additive angular margins) to increase the feature margin from the perspective of ground truth class. Both of them have been well-verified to learn discriminative features. However, they suffer from either the ambiguity of hard examples or the lack of discriminative power of other classes. In this paper, we design a novel loss function, namely support vector guided softmax loss (SV-Softmax), which adaptively emphasizes the mis-classified points (support vectors) to guide the discriminative features learning. So the developed SV-Softmax loss is able to eliminate the ambiguity of hard examples as well as absorb the discriminative power of other classes, and thus results in more discrimiantive features. To the best of our knowledge, this is the first attempt to inherit the advantages of mining-based and margin-based losses into one framework. Experimental results on several benchmarks have demonstrated the effectiveness of our approach over state-of-the-arts.