cGANs with Multi-Hinge Loss
Not on the map. Why?
Abstract (arXiv)
We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings. We study the compromise between training a state of the art generator and an accurate classifier simultaneously, and propose a way to use our algorithm to measure the degree to which a generator and critic are class conditional. We show the trade-off between a generator-critic pair respecting class conditioning inputs and generating the highest quality images. With our multi-hinge loss modification we are able to improve Inception Scores and Frechet Inception Distance on the Imagenet dataset. We make our tensorflow code available at https://github.com/ilyakava/gan.
Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Dec 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 2; 2023: 1.
8 papers.
- 2022Improving GANs for Long-Tailed Data through Group Spectral Regularizationcited by 14
- 2021Efficient Conditional GAN Transfer with Knowledge Propagation across Classescited by 13
- 2021The Nuts and Bolts of Adopting Transformer in GANscited by 2
- 2023CoopInit: Initializing Generative Adversarial Networks via Cooperative Learningcited by 2
- 2021Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Datacited by 1
- 2021A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attentioncited by 1
- 2021Physical Context and Timing Aware Sequence Generating GANscited by 0
- 2022Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networkscited by 0
- 2023CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning21 Mar 2023
- 2022Improving GANs for Long-Tailed Data through Group Spectral Regularization21 Aug 2022
- 2022Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks25 Jul 2022
- 2021The Nuts and Bolts of Adopting Transformer in GANs25 Oct 2021
- 2021Physical Context and Timing Aware Sequence Generating GANs28 Sep 2021
- 2021A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention18 Jun 2021
- 2021Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data21 Feb 2021
- 2021Efficient Conditional GAN Transfer with Knowledge Propagation across Classes12 Feb 2021