Unsupervised convolutional neural networks for large-scale image clustering

Chih Chung Hsu, Chia Wen Lin

研究成果: Conference contribution

9 引文 斯高帕斯(Scopus)

摘要

The paper proposes an unsupervised convolutional neural network (UCNN) to solve clustering and representation learning jointly in an iterative manner. The key idea behind the proposed method is that learning better feature representations of images leads to more accurate image clustering results, whereas better image clustering can benefit the feature learning with the proposed UCNN. In the proposed method, given an input image set, we first randomly pick k samples and extract their features as the initial centroids of image clusters using the proposed UCNN with an initial representation model pre-trained from the ImageNet dataset. Mini-batch k-means is then performed to assign cluster labels to individual input samples for a mini-batch of images randomly sampled from the input image set until all images are processed. Subsequently, UCNN simultaneously updates the parameters of UCNN and the centroids of image clusters iteratively based on stochastic gradient descent. Experimental results demonstrate the proposed method outperforms start-of-the-art clustering schemes in terms of accuracy and memory complexity on large-scale image sets containing millions of images.

原文English
主出版物標題2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
發行者IEEE Computer Society
頁面390-394
頁數5
ISBN(電子)9781509021758
DOIs
出版狀態Published - 2017 7月 2
事件24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
持續時間: 2017 9月 172017 9月 20

出版系列

名字Proceedings - International Conference on Image Processing, ICIP
2017-September
ISSN(列印)1522-4880

Conference

Conference24th IEEE International Conference on Image Processing, ICIP 2017
國家/地區China
城市Beijing
期間17-09-1717-09-20

All Science Journal Classification (ASJC) codes

  • 軟體
  • 電腦視覺和模式識別
  • 訊號處理

指紋

深入研究「Unsupervised convolutional neural networks for large-scale image clustering」主題。共同形成了獨特的指紋。

引用此