Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning
Hojin Park, Jaewoo Park, and Andrew Beng Jin Teoh

TL;DR
This paper introduces a fine-tuning approach with classifier weight imprinting and a novel Neighborhood Aware Cosine matcher to improve open-set face identification with few-shot galleries, emphasizing rejection of unknown identities.
Contribution
It proposes a new fine-tuning scheme and a Neighborhood Aware Cosine matcher to enhance open-set face identification accuracy and rejection capability.
Findings
Effective on large-scale face benchmarks
Improves rejection of unknown identities
Outperforms naive fine-tuning methods
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFace recognition and analysis · Biometric Identification and Security · Face and Expression Recognition
MethodsAttentive Walk-Aggregating Graph Neural Network
