Collapse resistant deep convolutional GAN for multi-object image generation

Elijah Bolluyt, Cristina Comaniciu

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

2 Scopus citations

Abstract

This work introduces a novel system for the generation of images that contain multiple classes of objects. Recent work in Generative Adversarial Networks have produced high quality images, but many focus on generating images of a single object or set of objects. Our system addresses the task of image generation conditioned on a list of desired classes to be included in a single image. This enables our system to generate images with any given combination of objects, all composed into a visually realistic natural image. The system learns the interrelationships of all classes represented in a dataset, and can generate diverse samples including a set of these classes. It displays the ability to arrange these objects together, accounting for occlusions and inter-object spatial relations that characterize complex natural images. To accomplish this, we introduce a novel architecture based on Conditional Deep Convolutional GANs that is stabilized against collapse relative to both mode and condition. The system learns to rectify mode collapse during training, self-correcting to avoid suboptimal generation modes.

Original languageEnglish
Title of host publicationProceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019
EditorsM. Arif Wani, Taghi M. Khoshgoftaar, Dingding Wang, Huanjing Wang, Naeem Seliya
Pages1404-1408
Number of pages5
ISBN (Electronic)9781728145495
DOIs
StatePublished - Dec 2019
Event18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 - Boca Raton, United States
Duration: 16 Dec 201919 Dec 2019

Publication series

NameProceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

Conference

Conference18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019
Country/TerritoryUnited States
CityBoca Raton
Period16/12/1919/12/19

Keywords

  • Conditional Generation
  • Generative Adversarial Networks
  • Image Generation
  • Minibatch Discrimination
  • Multi-class generation
  • Multi-class images
  • Multi-object Images
  • Multi-object generation

Fingerprint

Dive into the research topics of 'Collapse resistant deep convolutional GAN for multi-object image generation'. Together they form a unique fingerprint.

Cite this