The Cramér-InfoGAN and Partial Inverse Filter System for Unsupervised Image Classification

Shikun Zhang, Xiaoxue Feng, Yufeng Ji, Feng Pan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The scarcity of labelled data and the abundance of raw data have endowed unsupervised approaches to image classification with great significance. To enable learning in domains where labelled data are few, an unsupervised image classification system consisting of Cramér-InfoGAN and Partial Inverse Filter is proposed in this article. The former learns disentangled representation of data and builds a mapping from it to images, which is the main functionality of InfoGAN. Moreover, it combines Cramér GAN to improve the stability and convergence of training, also to monitor the reliability of learned representation by observing the energy distance of Cramér GAN. The latter classifies images by mapping it back to its representation. Furthermore, it is regularized by gradient penalty to suppress noise and by independence constraint to reduce entanglement of different dimensions. Experiments on MNIST and CIFAR-10 datasets show improved convergence and respectable classification accuracy of the system.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages348-353
Number of pages6
ISBN (Electronic)9781538636497
DOIs
Publication statusPublished - 25 May 2018
Event2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018 - Shanghai, China
Duration: 15 Jan 201818 Jan 2018

Publication series

NameProceedings - 2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018

Conference

Conference2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018
Country/TerritoryChina
CityShanghai
Period15/01/1818/01/18

Keywords

  • gradient penalty
  • independence constraint
  • unsupervised classification

Fingerprint

Dive into the research topics of 'The Cramér-InfoGAN and Partial Inverse Filter System for Unsupervised Image Classification'. Together they form a unique fingerprint.

Cite this

Zhang, S., Feng, X., Ji, Y., & Pan, F. (2018). The Cramér-InfoGAN and Partial Inverse Filter System for Unsupervised Image Classification. In Proceedings - 2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018 (pp. 348-353). Article 8367138 (Proceedings - 2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigComp.2018.00058