TL;DR本研究使用多种类别的条件生成模型推断真实数据的类别标签,并使用分类器在真实数据上进行标签预测,提出了分类准确度评分(CAS)作为新的模型评价指标。实验证明基于自注意力模型的生成模型在 CAS 上显著优于反卷积生成对抗网络模型。
Abstract
deep generative models (DGMs) of images are now sufficiently mature that they
produce nearly photorealistic samples and obtain scores similar to the data
distribution on heuristics such as Frechet Inception Dista