期刊
TSINGHUA SCIENCE AND TECHNOLOGY
卷 26, 期 4, 页码 536-547出版社
TSINGHUA UNIV PRESS
DOI: 10.26599/TST.2020.9010024
关键词
incremental face clustering; supervised learning; Graph Convolutional Network (GCN); optimal summary learning
类别
资金
- National Natural Science Foundation of China [61701277, 61771288]
- State Key Development Program in 13th Five-Year [2016YFB0801301, 044007008, 2016YFB1001005]
- National Engineering Laboratory for Intelligent Video Analysis and Application of China
This study proposes a new method to address the issues encountered in incremental face clustering by predicting summaries of previous data and exploring an efficient clustering framework. Experiments show that the proposed approach significantly outperforms existing incremental face clustering methods, with comparable accuracy to state-of-the-art static face clustering methods while consuming much less time.
In this study, we address the problems encountered by incremental face clustering. Without the benefit of having observed the entire data distribution, incremental face clustering is more challenging than static dataset clustering. Conventional methods rely on the statistical information of previous clusters to improve the efficiency of incremental clustering; thus, error accumulation may occur. Therefore, this study proposes to predict the summaries of previous data directly from data distribution via supervised learning. Moreover, an efficient framework to cluster previous summaries with new data is explored. Although learning summaries from original data costs more than those from previous clusters, the entire framework consumes just a little bit more time because clustering current data and generating summaries for new data share most of the calculations. Experiments show that the proposed approach significantly outperforms the existing incremental face clustering methods, as evidenced by the improvement of average F-score from 0.644 to 0.762. Compared with state-of-the-art static face clustering methods, our method can yield comparable accuracy while consuming much less time.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据