We’ve got mentioned all these strategies earlier in regression with tabular cross section data, now we’ll simply apply these for picture knowledge.
1.b.1. AutoEncoders (AE) :
- AE with FFNN
- AE with CNN (works higher for photographs knowledge)
1.b.2. Variational AutoEncoders (VAE) :
- VAE with FFNN
- VAE with CNN (works higher for photographs)
1.b.3. Vector Quantized — Variational Autoencoders (VQ-VAE) :
- VQ-VAE with FFNN
- VQ-VAE with CNN (works higher for photographs)
1.b.4. Generative Adversarial Networks (GANs) :
- GAN with FNN
- GAN with CNN (works higher for photographs)
- Latent GAN with FNN
- Latent GAN with CNN (works higher for photographs)
1.b.5. VAE — GAN :
- VAE-GAN with FFNN
- VAE-GAN with CNN (works higher for photographs)
- Latent VAE-GAN with FFNN
- Latent VAE-GAN with CNN (works higher for photographs)
1.b.6. VQ — GAN :
- VQ-VAE with FFNN
- VQ-VAE with CNN (works higher for photographs)
- Latent VQ-VAE with FFNN
- Latent VQ-VAE with CNN (works higher for photographs)
1.b.7. Denoising Diffusion Probabilistic Models (DDPMs) :
- DDPM with FFNN
- DDPM with CNN (works higher for photographs)
- Latent DDPM with FFNN
- Latent DDPM with CNN (works higher for photographs)
1.b.8. Denoising Diffusion Implicit Fashions (DDIMs) :
- DDIM with FFNN
- DDIM with CNN (works higher for photographs)
- Latent DDIM with FFNN
- Latent DDIM with CNN (works higher for photographs)
