Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition

TL;DR

This paper introduces the Unknown Identity Rejection (UIR) loss, a novel method that leverages unlabeled data to improve face recognition by effectively rejecting unknown identities and enhancing discriminative features.

Contribution

The paper proposes the UIR loss that utilizes unlabeled data to improve face recognition by rejecting unknown identities and increasing feature discriminativeness.

Findings

Performance improvement demonstrated on face recognition benchmarks.

Effective rejection of unknown identities in unconstrained environments.

Enhanced discriminative power of face features.

Abstract

Face recognition has advanced considerably with the availability of large-scale labeled datasets. However, how to further improve the performance with the easily accessible unlabeled dataset remains a challenge. In this paper, we propose the novel Unknown Identity Rejection (UIR) loss to utilize the unlabeled data. We categorize identities in unconstrained environment into the known set and the unknown set. The former corresponds to the identities that appear in the labeled training dataset while the latter is its complementary set. Besides training the model to accurately classify the known identities, we also force the model to reject unknown identities provided by the unlabeled dataset via our proposed UIR loss. In order to 'reject' faces of unknown identities, centers of the known identities are forced to keep enough margin from centers of unknown identities which are assumed to be approximated by the features of their samples. By this means, the discriminativeness of the face representations can be enhanced. Experimental results demonstrate that our approach can provide obvious performance improvement by utilizing the unlabeled data.