Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder
By Hyung-Gi Ham, Tae Joon Jun, Daeyoung Kim. 2020
27 citations recorded by the source corpus.
We propose Unbalanced GANs, which pre-trains the generator of the generative adversarial network (GAN) using variational autoencoder (VAE). We guarantee the stable training of the generator by preventing the faster convergence of the discriminator at early epochs. Furthermore, we balance between the generator and the discriminator at early epochs and thus maintain the stabilized training of GANs. We apply Unbalanced GANs to well known public datasets and find that Unbalanced GANs reduce mode collapses. We also show that Unbalanced GANs outperform ordinary GANs in terms of stabilized learning, faster convergence and better image quality at early epochs.
Subfields: Computer Vision and Pattern Recognition, Generative Models
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Kashyap Chitta
- Axel Sauer
- Andreas Geiger
- Jens Muller
- Luc Van Gool
- Ming-Hsuan Yang
- Jitendra Malik
- Xiaogang Wang
In Generative Models
- Axel Sauer
- Andreas Geiger
- Jens Muller
- Kashyap Chitta
- Tero Karras
- Timo Aila
- Yang Song
- Prafulla Dhariwal
Citations in the corpus
- Projected GANs Converge Faster (2021, background): “Work on leveraging pretrained representations for GANs can be divided into two categories: First, transferring parts of a GAN to a new dataset [15, 38, 65, 71] and, second, using pretrained models to control and improve GANs.”