Improved Training with Curriculum GANs

By Rishi Sharma, Shane T. Barratt, Stefano Ermon, Vijay S. Pande. 2018

15 citations recorded by the source corpus.

In this paper we introduce Curriculum GANs, a curriculum learning strategy for training Generative Adversarial Networks that increases the strength of the discriminator over the course of training, thereby making the learning task progressively more difficult for the generator. We demonstrate that this strategy is key to obtaining state-of-the-art results in image generation. We also show evidence that this strategy may be broadly applicable to improving GAN training in other data modalities.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Bernt Schiele
2. Edgar Schönfeld
3. Samuli Laine
4. Timo Aila
5. Anna Khoreva
6. Tero Karras
7. Zeynep Akata
8. Andrew Zisserman

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Bernt Schiele
3. Ming-Hsuan Yang
4. Dacheng Tao
5. Chen Change Loy
6. Trevor Darrell
7. Xiaogang Wang
8. Jitendra Malik

In Generative Models

1. Tero Karras
2. Timo Aila
3. Samuli Laine
4. Anna Khoreva
5. Richard Zhang
6. Jun-Yan Zhu
7. Eli Shechtman
8. Bolei Zhou

Citations in the corpus

• A Style-Based Generator Architecture for Generative Adversarial Networks (2018, methodology): “, using multiple discriminators [17, 43, 10], multiresolution discrimination [55, 51], or self-attention [57].”
• A U-Net Based Discriminator for Generative Adversarial Networks (2020, background): “Other lines of work focused mainly on improving the discriminator by exploiting multiple [36, 13, 11] and multi-resolution [45, 42] discriminators, using spatial feedback of the discriminator [17], an auto-encoder architecture with the reconstructionbased feedback to the generator [52] or self-super”