Joint Pairwise Learning and Image Clustering Based on a Siamese CNN

Weng Tai Su, Chih Chung Hsu, Ziling Huang, Chia Wen Lin, Gene Cheung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

How to use a deep convolutional neural network (CNN) to efficiently and effectively learn representations of a large unlabeled set of images and group them into clusters remains a challenging problem. To address this problem, we propose a Siamese clustering CNN (SC-CNN) to iteratively learn discriminative representations for image clustering. Based on the proposed SC-CNN, we employ a mini-batch-based joint pairwise representation learning and clustering scheme to make the computation and storage cost efficient for large-scale image clustering on a personal computer with a commercial GPU graphic card. On top of SC-CNN, the proposed pairwise learning scheme effectively learns discriminative representations by appropriately selecting same-cluster and different-cluster image pairs from the results of each clustering iteration. Experimental results demonstrate that the proposed method outperforms start-of-the-art clustering schemes in clustering accuracy on public image sets.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages1992-1996
Number of pages5
ISBN (Electronic)9781479970612
DOIs
Publication statusPublished - 2018 Aug 29
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: 2018 Oct 72018 Oct 10

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
Country/TerritoryGreece
CityAthens
Period18-10-0718-10-10

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Joint Pairwise Learning and Image Clustering Based on a Siamese CNN'. Together they form a unique fingerprint.

Cite this