Self-learning for face clustering

Self-learning for face clustering
复制标题

自学习人脸聚类

DOI:
10.1016/j.patcog.2018.02.008
复制
发表时间:
2018-07
影响因子:
8
通讯作者:
Yang Lin
Yang Lin
中科院分区:
计算机科学1区
文献类型:
--
作者:
Shi Xiaoshuang;Guo Zhenhua;Xing Fuyong;Cai Jinzheng;Yang Lin

文献摘要

参考文献

被引文献

相似文献

本文模拟人类的学习方式,提出了一种人脸聚类的自学习框架。具体地说,我们首先通过基于面片的二维重建对人脸图像进行去相关操作,该操作具有类似于视网膜的功能。然后,我们使用一种新的自进度学习模型对语义相似的人脸进行分组,该模型受到三个主要观察结果的启发:(1)人类的学习过程逐渐从简单到复杂的任务进行;(2)人类的先验知识可能会随着学习经验的增加而变化;(3)更多的先验知识通常会导致更好的预测精度。在基准人脸数据库上的实验证明了该框架的有效性和高效性。
In this paper, we simulate the learning way of human to propose a self-learning framework for face clustering. Specifically, we first perform a decorrelation operation on face images through patch-based two-dimensional reconstruction, which has a similar function to the retina. Then we group the semantically similar faces by using a novel self-paced learning model, which is inspired by three major observations: (i) The learning process of human gradually proceeds from easy to complex tasks; (ii) The prior knowledge of human might change with the increase of learned experience; (iii) More prior knowledge usually leads to better prediction accuracy. Experiments on benchmark face databases demonstrate the effectiveness and efficiency of the proposed framework.
DOI: 10.1037/h0054663
发表时间: 1954-01-01
影响因子: 5.4
作者:
ATTNEAVE, F
通讯作者: ATTNEAVE, F
DOI: 10.1002/0471602396.ch14
发表时间: 2004-09
期刊: Statistical Methods for Biomedical Research
影响因子: --
作者:
G. Belle;L. Fisher;P. Heagerty;T. Lumley
通讯作者: G. Belle;L. Fisher;P. Heagerty;T. Lumley
DOI: 10.1007/978-1-4615-1637-8
发表时间: 2001
期刊: --
影响因子: --
作者:
M. Bartlett
通讯作者: M. Bartlett
DOI: 10.1109/tip.2015.2405474
发表时间: 2015-02
影响因子: 10.6
作者:
Xiaoshuang Shi;Zhenhua Guo;Zhihui Lai;Yujiu Yang;Z. Bao;D. Zhang
通讯作者: Xiaoshuang Shi;Zhenhua Guo;Zhihui Lai;Yujiu Yang;Z. Bao;D. Zhang
DOI: 10.1109/iccv.2005.127
发表时间: 2005-10
期刊: Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
影响因子: --
作者:
Jian Yang;David Zhang;Jing-yu Yang
通讯作者: Jian Yang;David Zhang;Jing-yu Yang