SAGAN

2000년 도입 · 논문 138편에서 사용

The Self-Attention Generative Adversarial Network, or SAGAN, allows for attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points in lower-resolution feature maps. In SAGAN, details can be generated using cues from all feature locations. Moreover, the discriminator can check that highly detailed features in distant portions of the image are consistent with each other.

출처: Self-Attention Generative Adversarial Networks

소개 논문: Self-Attention Generative Adversarial Networks