English

Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning

Computer Vision and Pattern Recognition 2023-01-09 v1

Abstract

In this paper, we focus on addressing the open-set face identification problem on a few-shot gallery by fine-tuning. The problem assumes a realistic scenario for face identification, where only a small number of face images is given for enrollment and any unknown identity must be rejected during identification. We observe that face recognition models pretrained on a large dataset and naively fine-tuned models perform poorly for this task. Motivated by this issue, we propose an effective fine-tuning scheme with classifier weight imprinting and exclusive BatchNorm layer tuning. For further improvement of rejection accuracy on unknown identities, we propose a novel matcher called Neighborhood Aware Cosine (NAC) that computes similarity based on neighborhood information. We validate the effectiveness of the proposed schemes thoroughly on large-scale face benchmarks across different convolutional neural network architectures. The source code for this project is available at: https://github.com/1ho0jin1/OSFI-by-FineTuning

Keywords

Cite

@article{arxiv.2301.01922,
  title  = {Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning},
  author = {Hojin Park and Jaewoo Park and Andrew Beng Jin Teoh},
  journal= {arXiv preprint arXiv:2301.01922},
  year   = {2023}
}
R2 v1 2026-06-28T08:03:22.385Z