Large-Margin Softmax Loss for Convolutional Neural Networks

TL;DR

This paper introduces a generalized large-margin softmax loss for CNNs that enhances feature discriminability by explicitly promoting intra-class compactness and inter-class separability, leading to improved performance.

Contribution

The paper proposes a novel L-Softmax loss that explicitly encourages discriminative feature learning and can be optimized with standard stochastic gradient descent.

Findings

L-Softmax improves feature discriminability in CNNs

Significant performance boost on multiple benchmark datasets

Effective in visual classification and verification tasks

Abstract

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin softmax (L-Softmax) loss which explicitly encourages intra-class compactness and inter-class separability between learned features. Moreover, L-Softmax not only can adjust the desired margin but also can avoid overfitting. We also show that the L-Softmax loss can be optimized by typical stochastic gradient descent. Extensive experiments on four benchmark datasets demonstrate that the deeply-learned features with L-softmax loss become more discriminative, hence significantly boosting the performance on a variety of visual classification and verification tasks.