VQ-VAE-2

2000년 도입 · 논문 7편에서 사용

VQ-VAE-2 is a type of variational autoencoder that combines a a two-level hierarchical VQ-VAE with a self-attention autoregressive model (PixelCNN) as a prior. The encoder and decoder architectures are kept simple and light-weight as in the original VQ-VAE, with the only difference that hierarchical multi-scale latent maps are used for increased resolution.

출처: Generating Diverse High-Fidelity Images with VQ-VAE-2

소개 논문: Generating Diverse High-Fidelity Images with VQ-VAE-2