本文に飛ぶ
その他

VariFace: Fair and Diverse Synthetic Dataset Generation for Face Recognition

VariFace: Fair and Diverse Synthetic Dataset Generation for Face Recognition

資料種別
その他
著者
鈴木, 健二ほか
出版者
-
出版年
2024-12
資料形態
ページ数・大きさ等
-
NDC
-
すべて見る

資料に関する注記

一般注記:

出版タイプ: AOThe use of large-scale, web-scraped datasets to train face recognition models has raised significant privacy and bias concerns. Synthetic met...

書店で探す

全国の図書館の所蔵

国立国会図書館以外の全国の図書館の所蔵状況を表示します。

所蔵のある図書館から取寄せることが可能かなど、資料の利用方法は、ご自身が利用されるお近くの図書館へご相談ください

その他

  • 東京科学大学リサーチリポジトリ(T2R2)

    連携先のサイトで、学術機関リポジトリデータベース(IRDB)(機関リポジトリ)が連携している機関・データベースの所蔵状況を確認できます。

書誌情報

この資料の詳細や典拠(同じ主題の資料を指すキーワード、著者名)等を確認できます。

資料種別
その他
著者・編者
鈴木, 健二
Suzuki, Kenji
出版年月日等
2024-12
出版年(W3CDTF)
2024
並列タイトル等
VariFace: Fair and Diverse Synthetic Dataset Generation for Face Recognition
タイトル(掲載誌)
arXiv preprint
対象利用者
一般
一般注記
出版タイプ: AO
The use of large-scale, web-scraped datasets to train face recognition models has raised significant privacy and bias concerns. Synthetic methods mitigate these concerns and provide scalable and controllable face generation to enable fair and accurate face recognition. However, existing synthetic datasets display limited intraclass and interclass diversity and do not match the face recognition performance obtained using real datasets. Here, we propose VariFace, a two-stage diffusion-based pipeline to create fair and diverse synthetic face datasets to train face recognition models. Specifically, we introduce three methods: Face Recognition Consistency to refine demographic labels, Face Vendi Score Guidance to improve interclass diversity, and Divergence Score Conditioning to balance the identity preservation-intraclass diversity trade-off. When constrained to the same dataset size, VariFace considerably outperforms previous synthetic datasets (0.9200 → 0.9405) and achieves comparable performance to face recognition models trained with real data (Real Gap = -0.0065). In an unconstrained setting, VariFace not only consistently achieves better performance compared to previous synthetic methods across dataset sizes but also, for the first time, outperforms the real dataset (CASIA-WebFace) across six evaluation datasets. This sets a new state-of-the-art performance with an average face verification accuracy of 0.9567 (Real Gap = +0.0097) across LFW, CFP-FP, CPLFW, AgeDB, and CALFW datasets and 0.9366 (Real Gap = +0.0380) on the RFW dataset.
identifier:oai:t2r2.star.titech.ac.jp:50722059