DuaFace: Data uncertainty in angular based loss for face recognition

Published: 01 Jan 2023, Last Modified: 02 Oct 2024Pattern Recognit. Lett. 2023EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Prevents model from overfitting on noisy and low-quality samples.•Loss function introduces Data Uncertainty to face recognition.•Accuracy over existing loss functions on most public benchmarks.•A general face recognition loss function.
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview