Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.19074 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915212929531904 |
|---|---|
| author | Goni, Osman Arka, Himadri Saha Halder, Mithun Shibly, Mir Moynuddin Ahmed Shatabda, Swakkhar |
| author_facet | Goni, Osman Arka, Himadri Saha Halder, Mithun Shibly, Mir Moynuddin Ahmed Shatabda, Swakkhar |
| contents | Recent advances in Generative Adversarial Networks (GANs) have demonstrated their capability for producing high-quality images. However, a significant challenge remains mode collapse, which occurs when the generator produces a limited number of data patterns that do not reflect the diversity of the training dataset. This study addresses this issue by proposing a number of architectural changes aimed at increasing the diversity and stability of GAN models. We start by improving the loss function with Wasserstein loss and Gradient Penalty to better capture the full range of data variations. We also investigate various network architectures and conclude that ResNet significantly contributes to increased diversity. Building on these findings, we introduce HingeRLC-GAN, a novel approach that combines RLC Regularization and the Hinge loss function. With a FID Score of 18 and a KID Score of 0.001, our approach outperforms existing methods by effectively balancing training stability and increased diversity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19074 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HingeRLC-GAN: Combating Mode Collapse with Hinge Loss and RLC Regularization Goni, Osman Arka, Himadri Saha Halder, Mithun Shibly, Mir Moynuddin Ahmed Shatabda, Swakkhar Machine Learning Artificial Intelligence Recent advances in Generative Adversarial Networks (GANs) have demonstrated their capability for producing high-quality images. However, a significant challenge remains mode collapse, which occurs when the generator produces a limited number of data patterns that do not reflect the diversity of the training dataset. This study addresses this issue by proposing a number of architectural changes aimed at increasing the diversity and stability of GAN models. We start by improving the loss function with Wasserstein loss and Gradient Penalty to better capture the full range of data variations. We also investigate various network architectures and conclude that ResNet significantly contributes to increased diversity. Building on these findings, we introduce HingeRLC-GAN, a novel approach that combines RLC Regularization and the Hinge loss function. With a FID Score of 18 and a KID Score of 0.001, our approach outperforms existing methods by effectively balancing training stability and increased diversity. |
| title | HingeRLC-GAN: Combating Mode Collapse with Hinge Loss and RLC Regularization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.19074 |