.png){kind=icon}
返回
Data augmentation for unbalanced face recognition training sets
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2016.12.013.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Face recognition remains a challenging problem. While one-to-one face verification has been largely tackled, verification-based classification problem still demands effort. To further enhance the verification models, one solution is to fully utilize the unbalanced training sets, where, while abundant samples are provided for some subjects, there are often so few samples available for the rest. These subjects with too few samples can contribute little to the model learning. Therefore, before training a model, algorithms usually perform data augmentation on the whole dataset, especially on subjects with insufficient samples. In this paper, a new augmentation method is proposed, targeting on data augmentation for face classification algorithms. Instead of directly manipulating the input image, we perform virtual sample generating on feature level. The distribution of feature maps is first estimated, then random noise consistent to the distribution is applied to the feature vectors of training samples. Our method is based on Joint Bayesian Face Analysis, and we also develop an algorithm to boost the whole procedure. We conduct experiments based on high dimensional LBP features and features extracted by a shallow Convolutional Neural Network, and succeed to verify the effectiveness of this method, using image data from benchmark dataset LFW.
Keyword:
Data Augmentation
Face Recognition
Convolutional Neural Network
Support Vector Machine
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Flexible Energy-Efficient Implementation of Adaptive Spiking Encoder for Neuromorphic Processors
PREAI
分享收藏OPPOSITE CHANGES IN THE EXPRESSION OF ENKEPHALIN IN THE AMYGDALA AND HYPOTHALAMUS AFTER LESIONS OF THE BED NUCLEUS OF THE STRIA TERMINALIS IN THE RAT.png)
Neuroscience
NeuroscienceIF0
PREAI
分享收藏Identification of the optimal ground motion intensity measure and input parameters for assessing liquefaction-induced lateral spreading based on the generalized additive method基于广义加法模型识别评估液化引起的侧向扩展的最优地面运动强度指标和输入参数ACTA GEOTECHNICA
ACTA GEOTECHNICAIF5.7
PREAI
分享收藏Addressing the Challenge to Create a Sustainable Future for All-It Takes a Village应对为所有人创造可持续未来的挑战——众人拾柴火焰高ACS ENERGY LETTERS
ACS ENERGY LETTERSIF18.2
PREAI
分享收藏Scaling Up the Catalytic Hydrogen Generation on a Rh-Cu@Ti3C2T x -CN System: A Strategic Approach for Green Fuel Production在Rh-Cu@Ti3C2T x -CN体系上扩大催化氢气生成规模：一种绿色燃料生产的战略方法
PREAI
分享收藏 没有更多内容
没有更多内容