cGANs with Multi-Hinge Loss
By Ilya Kavalerov, Wojciech Czaja, Ramalingam Chellappa. 2019
23 citations recorded by the source corpus.
We propose a new algorithm to incorporate class conditional information into the discriminator of GANs via a multi-class generalization of the commonly used Hinge loss. Our approach is in contrast to most GAN frameworks in that we train a single classifier for K+1 classes with one loss function, instead of a real/fake discriminator, or a discriminator classifier pair. We show that learning a single good classifier and a single state of the art generator simultaneously is possible in supervised and semi-supervised settings. With our multi-hinge loss modification we were able to improve the state of the art CIFAR10 IS & FID to 9.58 & 6.40, CIFAR100 IS & FID to 14.36 & 13.32, and STL10 IS & FID to 12.16 & 17.44. The code written with PyTorch is available at this https URL.
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
- Luc Van Gool
- Ming-Hsuan Yang
- Antonio Torralba
- Jun-Yan Zhu
- Eli Shechtman
- Dacheng Tao
- Richard Zhang
- Chen Change Loy
In Generative Models
- Eli Shechtman
- Jun-Yan Zhu
- Richard Zhang
- Tero Karras
- Daniel Cohen-Or
- Timo Aila
- Samuli Laine
- Jaakko Lehtinen
Citations in the corpus
- Training Generative Adversarial Networks with Limited Data (2020, background): “The best IS and FID were searched separately [22], and often came from different snapshots.”