The 2 Stages
There are mainly 2 stages when training a generative model.
1. Perceptual Compression
- Process of removing high-frequency details
- Encapsulate data into an abstract representation
- GANS accomplish this by projecting data from pixel space to a hyperspace called latent space.
2. Semantic Compression
- Capture semantic structure present in data
- Preservation of the context and inter-relationship of various objects
- Transformers are good at capturing semantic structures
