Face Recognition via Centralized Coordinate Learning

TL;DR

This paper introduces a centralized coordinate learning (CCL) method for face recognition that improves feature dispersion and discrimination, achieving high performance across multiple benchmarks with limited training data.

Contribution

The paper proposes a novel CCL approach that jointly learns face features and classification vectors, with an adaptive angular margin to enhance discrimination.

Findings

Consistently competitive results on six face benchmarks.

Effective with small-scale training data.

Improves feature dispersion and discrimination.

Abstract

Owe to the rapid development of deep neural network (DNN) techniques and the emergence of large scale face databases, face recognition has achieved a great success in recent years. During the training process of DNN, the face features and classification vectors to be learned will interact with each other, while the distribution of face features will largely affect the convergence status of network and the face similarity computing in test stage. In this work, we formulate jointly the learning of face features and classification vectors, and propose a simple yet effective centralized coordinate learning (CCL) method, which enforces the features to be dispersedly spanned in the coordinate space while ensuring the classification vectors to lie on a hypersphere. An adaptive angular margin is further proposed to enhance the discrimination capability of face features. Extensive experiments are conducted on six face benchmarks, including those have large age gap and hard negative samples. Trained only on the small-scale CASIA Webface dataset with 460K face images from about 10K subjects, our CCL model demonstrates high effectiveness and generality, showing consistently competitive performance across all the six benchmark databases.