SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916159026102272 |
|---|---|
| author | Jeon, Jinsung Park, Noseong |
| author_facet | Jeon, Jinsung Park, Noseong |
| contents | Score-based generative models (SGMs) show the state-of-the-art sampling quality and diversity. However, their training/sampling complexity is notoriously high due to the highly complicated forward/reverse processes, so they are not suitable for resource-limited settings. To solving this problem, learning a simpler process is gathering much attention currently. We present an enhanced GAN-based denoising method, called SPI-GAN, using our proposed straight-path interpolation definition. To this end, we propose a GAN architecture i) denoising through the straight-path and ii) characterized by a continuous mapping neural network for imitating the denoising path. This approach drastically reduces the sampling time while achieving as high sampling quality and diversity as SGMs. As a result, SPI-GAN is one of the best-balanced models among the sampling quality, diversity, and time for CIFAR-10, and CelebA-HQ-256. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2206_14464 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations Jeon, Jinsung Park, Noseong Machine Learning Artificial Intelligence Score-based generative models (SGMs) show the state-of-the-art sampling quality and diversity. However, their training/sampling complexity is notoriously high due to the highly complicated forward/reverse processes, so they are not suitable for resource-limited settings. To solving this problem, learning a simpler process is gathering much attention currently. We present an enhanced GAN-based denoising method, called SPI-GAN, using our proposed straight-path interpolation definition. To this end, we propose a GAN architecture i) denoising through the straight-path and ii) characterized by a continuous mapping neural network for imitating the denoising path. This approach drastically reduces the sampling time while achieving as high sampling quality and diversity as SGMs. As a result, SPI-GAN is one of the best-balanced models among the sampling quality, diversity, and time for CIFAR-10, and CelebA-HQ-256. |
| title | SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2206.14464 |