BigGAN is a type of generative adversarial network that was designed for scaling generation to high-resolution, high-fidelity images. It includes a number of incremental changes and innovations. The baseline and incremental changes are:
The innovations are:
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Generation | 29 | 18.13% |
Conditional Image Generation | 12 | 7.50% |
Multi-agent Reinforcement Learning | 7 | 4.38% |
Reinforcement Learning (RL) | 6 | 3.75% |
Decision Making | 5 | 3.13% |
Super-Resolution | 4 | 2.50% |
Benchmarking | 3 | 1.88% |
Denoising | 3 | 1.88% |
Image Classification | 3 | 1.88% |