Knowledge Commons of Institute of Automation,CAS
Deep Self-Evolution Clustering | |
Chang, Jianlong1,2![]() ![]() ![]() ![]() ![]() | |
发表期刊 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
![]() |
ISSN | 0162-8828 |
2020-04-01 | |
卷号 | 42期号:4页码:809-823 |
摘要 | Clustering is a crucial but challenging task in pattern analysis and machine learning. Existing methods often ignore the combination between representation learning and clustering. To tackle this problem, we reconsider the clustering task from its definition to develop Deep Self-Evolution Clustering (DSEC) to jointly learn representations and cluster data. For this purpose, the clustering task is recast as a binary pairwise-classification problem to estimate whether pairwise patterns are similar. Specifically, similarities between pairwise patterns are defined by the dot product between indicator features which are generated by a deep neural network (DNN). To learn informative representations for clustering, clustering constraints are imposed on the indicator features to represent specific concepts with specific representations. Since the ground-truth similarities are unavailable in clustering, an alternating iterative algorithm called Self-Evolution Clustering Training (SECT) is presented to select similar and dissimilar pairwise patterns and to train the DNN alternately. Consequently, the indicator features tend to be one-hot vectors and the patterns can be clustered by locating the largest response of the learned indicator features. Extensive experiments strongly evidence that DSEC outperforms current models on twelve popular image, text and audio datasets consistently. |
关键词 | Task analysis Unsupervised learning Training Clustering methods Pattern analysis Clustering deep self-evolution clustering self-evolution clustering training deep unsupervised learning |
DOI | 10.1109/TPAMI.2018.2889949 |
关键词[WOS] | IMAGE RETRIEVAL ; REPRESENTATIONS |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61573352] ; Beijing Natural Science Foundation[L172053] |
项目资助者 | National Natural Science Foundation of China ; Beijing Natural Science Foundation |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000526541100004 |
出版者 | IEEE COMPUTER SOC |
七大方向——子方向分类 | 模式识别基础 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/38863 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Wang, Lingfeng |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Dept Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Chang, Jianlong,Meng, Gaofeng,Wang, Lingfeng,et al. Deep Self-Evolution Clustering[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2020,42(4):809-823. |
APA | Chang, Jianlong,Meng, Gaofeng,Wang, Lingfeng,Xiang, Shiming,&Pan, Chunhong.(2020).Deep Self-Evolution Clustering.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,42(4),809-823. |
MLA | Chang, Jianlong,et al."Deep Self-Evolution Clustering".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 42.4(2020):809-823. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
5-DSEC-IEEE TPAMI.pd(4817KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论