Image Clustering based on Deep Sparse Representations
Lv Le1; Zhao Dongbin1; Deng QingQiong2
2017-02
会议名称The 2016 IEEE Symposium Series on Computational Intelligence
会议日期6-9 Dec. 2016
会议地点Athens, Greece
摘要Currently, the supervised trained deep neural networks (DNNs) have been successfully applied in several image classification tasks. However, how to extract powerful data representations and discover semantic concepts from unlabeled data is a more practical issue. Unsupervised feature learning methods aim at extracting abstract representations from unlabeled data. Large amount of research works illustrate that these representations can be directly used in the supervised tasks. However, due to the high dimensionality of these representations, it is difficult to discover the categorical concepts among them in an unsupervised way. In this paper, we propose combining the winner-take-all autoencoder with the bipartite graph partitioning algorithm to cluster unlabeled image data. The winner-take-all autoencoder can learn the additive sparse representations. By the experiments, we present the properties of the sparse representations. The bipartite graph partitioning can take full advantage of them and generate semantic clusters. We discover that the confident instances in each cluster are well discriminated. Based on the initial clustering result, we further train a support vector machine (SVM) to refine the clusters. Our method can discover the categorical concepts rapidly and the experiment shows that the clustering performance of our method is good.
DOI10.1109/SSCI.2016.7850110
引用统计
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14471
专题复杂系统管理与控制国家重点实验室_深度强化学习
作者单位1.The State Key Laboratory of Management and Control for Complex Systems Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
2.College of Information Science and Technology, Beijing Normal University, Beijing, 100875, China
推荐引用方式
GB/T 7714
Lv Le,Zhao Dongbin,Deng QingQiong. Image Clustering based on Deep Sparse Representations[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
07850110.pdf(410KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Lv Le]的文章
[Zhao Dongbin]的文章
[Deng QingQiong]的文章
百度学术
百度学术中相似的文章
[Lv Le]的文章
[Zhao Dongbin]的文章
[Deng QingQiong]的文章
必应学术
必应学术中相似的文章
[Lv Le]的文章
[Zhao Dongbin]的文章
[Deng QingQiong]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 07850110.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。