Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train Generative Adversarial Networks at the largest scale yet attempted, and study the instabilities specific to such scale. We find that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick", allowing fine control over the trade-off between sample fidelity and variety by truncating the latent space. Our modifications lead to models which set the new state of the art in class-conditional image synthesis. When trained on ImageNet at 128x128 resolution, our models (BigGANs) achieve an Inception Score (IS) of 166.3 and Frechet Inception Distance (FID) of 9.6, improving over the previous best IS of 52.52 and FID of 18.65.

翻译：尽管最近在基因图像建模、成功生成高分辨率、来自图像网络等复杂数据集的各种样本方面有所进展,但目标仍难以实现。为此,我们培训了最大规模的基因反对子网络,但尝试过这种规模,并研究此类规模特有的不稳定性。我们发现,对发电机应用正方位正规化使其容易接受简单的“脱轨骗戏法”,从而通过对潜在空间进行脱轨,对样本忠诚性和多样性之间的权衡进行细微控制。我们的修改导致形成模型,在类状图像合成中设定艺术的新状态。在对图像网络进行128x128分辨率的培训后,我们的模型(BigGANs)达到166.3的感化分数,Frechet Inpeption距离(FID)达到9.6,比先前的最佳IS52.52和18.65的FID改进。