BigBiGAN

2000년 도입 · 논문 4편에서 사용

BigBiGAN is a type of BiGAN with a BigGAN image generator. The authors initially used ResNet as a baseline for the encoder $\mathcal{E}$ followed by a 4-layer MLP with skip connections, but they experimented with RevNets and found they outperformed with increased network width, so opted for this type of encoder for the final architecture.

출처: Large Scale Adversarial Representation Learning

소개 논문: Large Scale Adversarial Representation Learning