.png){kind=icon}
返回
DuaFace: Data uncertainty in angular based loss for face recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2023.01.013.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The Data Uncertainty inherently existed in feature continuous mapping space itself and the training dataset. In this paper, a general loss function DuaFace based on Data Uncertainty and Angular/cosine-margin-based loss is proposed to study the influence of Data Uncertainty on traditional Angular based loss functions. Correspondingly, insightful analysis on how incorporating Data Uncertainty estimation helps reducing the adverse effects of noisy samples and affects the process of feature learning are also provided. Moreover, extensive experiments conducted on Face Recognition demonstrate its superiority over state-of-the-arts. (c) 2023 Elsevier B.V. All rights reserved.
Keyword:
Face recognition
Loss function
Data uncertainty
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
.png){kind=icon}
A novel deep learning based framework for the detection and classification of breast cancer using transfer learning一种基于深度学习的新框架，用于使用迁移学习检测和分类乳腺癌
PREAI
分享收藏SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face RecognitionSFace: Sigmoid约束超球损失的鲁棒人脸识别
OAAI
OAAI分享收藏 没有更多内容
没有更多内容