L2-constrained Softmax Loss for Discriminative Face Verification

TL;DR

This paper introduces an L2-constraint to the softmax loss in deep face verification models, which improves the discriminative power of features and achieves state-of-the-art results on multiple datasets.

Contribution

The paper proposes a simple L2-constraint added to softmax loss, enhancing feature discriminability and boosting face verification performance.

Findings

Achieved 99.78% accuracy on LFW dataset.

Attained 0.909 TPR at 0.0001 FAR on IJB-A.

Significantly improved face verification results.

Abstract

In recent years, the performance of face verification systems has significantly improved using deep convolutional neural networks (DCNNs). A typical pipeline for face verification includes training a deep network for subject classification with softmax loss, using the penultimate layer output as the feature descriptor, and generating a cosine similarity score given a pair of face images. The softmax loss function does not optimize the features to have higher similarity score for positive pairs and lower similarity score for negative pairs, which leads to a performance gap. In this paper, we add an L2-constraint to the feature descriptors which restricts them to lie on a hypersphere of a fixed radius. This module can be easily implemented using existing deep learning frameworks. We show that integrating this simple step in the training pipeline significantly boosts the performance of face verification. Specifically, we achieve state-of-the-art results on the challenging IJB-A dataset, achieving True Accept Rate of 0.909 at False Accept Rate 0.0001 on the face verification protocol. Additionally, we achieve state-of-the-art performance on LFW dataset with an accuracy of 99.78%, and competing performance on YTF dataset with accuracy of 96.08%.