TL;DR本研究利用预训练的大规模 GAN 模型在有限数据情境下实现了对感知明显目标领域的图像生成,提出了自适应滤波器调制(AdaFM)的方法,证明了此技术在限制数据生成方面的有效性。
Abstract
Recent work has shown generative adversarial networks (gans) can generate
highly realistic images, that are often indistinguishable (by humans) from real
images. Most images so generated are not contained in the