Publications
Detailed Information
ContraGAN: Contrastive learning for conditional image generation
Cited 0 time in
Web of Science
Cited 83 time in Scopus
- Authors
- Issue Date
- 2020
- Citation
- Advances in Neural Information Processing Systems, Vol.2020-December
- Abstract
- Conditional image generation is the task of generating diverse images using class label information. Although many conditional Generative Adversarial Networks (GAN) have shown realistic results, such methods consider pairwise relations between the embedding of an image and the embedding of the corresponding label (data-to-class relations) as the conditioning losses. In this paper, we propose ContraGAN that considers relations between multiple image embeddings in the same batch (data-to-data relations) as well as the data-to-class relations by using a conditional contrastive loss. The discriminator of ContraGAN discriminates the authenticity of given samples and minimizes a contrastive objective to learn the relations between training images. Simultaneously, the generator tries to generate realistic images that deceive the authenticity and have a low contrastive loss. The experimental results show that ContraGAN outperforms state-of-the-art-models by 7.3% and 7.7% on Tiny ImageNet and ImageNet datasets, respectively. Besides, we experimentally demonstrate that contrastive learning helps to relieve the overfitting of the discriminator. For a fair comparison, we re-implement twelve state-of-the-art GANs using the PyTorch library. The software package is available at https://github.com/POSTECH-CVLab/PyTorch-StudioGAN.
- ISSN
- 1049-5258
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.