CIGAN: A novel GANs model based on category information

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

Abstract

Unsupervised learning with Generative Adversarial Networks (GANs) has made great achievements these years. Generally, traditional GANs model improve the generation effect by proposing new loss functions or adjusting network structures. However, the category information of training data is rarely used in the training of GANs network and the discriminative power of traditional GANs' discriminator is limited. To overcome such a problem, we propose an improved GANs model based on Category Information (CIGAN), which applies the hash center loss to improve the training speed of the CIGAN model. We also propose two methods for CIGAN model to improve the discrimination ability of discriminator network. The CIGAN model has advantages over traditional GANs model as it can generate higher quality images, and can remain stable during the learning process when the batch normalization layer is removed. The Inception score on the CIFAR-10 dataset also demonstrates that our model is better than traditional GANs model with higher generation effect.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovations, SmartWorld/UIC/ATC/ScalCom/CBDCom/IoP/SCI 2018
EditorsFrederic Loulergue, Guojun Wang, Md Zakirul Alam Bhuiyan, Xiaoxing Ma, Peng Li, Manuel Roveri, Qi Han, Lei Chen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages522-529
Number of pages8
ISBN (Electronic)9781538693803
DOIs
StatePublished - 4 Dec 2018
Event4th IEEE SmartWorld, 15th IEEE International Conference on Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovations, SmartWorld/UIC/ATC/ScalCom/CBDCom/IoP/SCI 2018 - Guangzhou, China
Duration: 7 Oct 201811 Oct 2018

Publication series

NameProceedings - 2018 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovations, SmartWorld/UIC/ATC/ScalCom/CBDCom/IoP/SCI 2018

Conference

Conference4th IEEE SmartWorld, 15th IEEE International Conference on Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovations, SmartWorld/UIC/ATC/ScalCom/CBDCom/IoP/SCI 2018
Country/TerritoryChina
CityGuangzhou
Period7/10/1811/10/18

Keywords

  • Category information
  • Discrimination ability
  • Hash center loss
  • Softmax function

Fingerprint

Dive into the research topics of 'CIGAN: A novel GANs model based on category information'. Together they form a unique fingerprint.

Cite this