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

Hojin Park, Jaewoo Park, Andrew Beng Jin Teoh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we focus on addressing the open-set face identification problem on a few-shot gallery by finetuning. 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

Original languageEnglish
Title of host publication2022 26th International Conference on Pattern Recognition, ICPR 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1026-1032
Number of pages7
ISBN (Electronic)9781665490627
DOIs
Publication statusPublished - 2022
Event26th International Conference on Pattern Recognition, ICPR 2022 - Montreal, Canada
Duration: 2022 Aug 212022 Aug 25

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2022-August
ISSN (Print)1051-4651

Conference

Conference26th International Conference on Pattern Recognition, ICPR 2022
Country/TerritoryCanada
CityMontreal
Period22/8/2122/8/25

Bibliographical note

Funding Information:
In this work we showed that combining weight-imprinted classifier and BatchNorm-only tuning of the encoder effectively improves the encoder’s OSFI performance without suffering from overfitting. We further facilitated the performance by our novel NAC matcher instead of the commonly used cosine similarity. Future works will explore extending this idea to the open-set few-shot recognition of generic images. Acknowledgements: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (NO. NRF-2022R1A2C1010710)

Publisher Copyright:
© 2022 IEEE.

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning'. Together they form a unique fingerprint.

Cite this