Training of generative adversarial network (GAN) on a video dataset is a challenge because of the sheer size of the dataset and the complexity of each observation. In general, the computational cost of training GAN scales exponentially with the resolution. In this study, we present a novel memory efficient method of unsupervised learning of high-resolution video dataset whose computational cost scales only linearly with the resolution. We achieve this by designing the generator model as a stack of small sub-generators and training the model in a specific way. We train each sub-generator with its own specific discriminator. At the time of the training, we introduce between each pair of consecutive sub-generators an auxiliary subsampling layer that reduces the frame-rate by a certain ratio. This procedure can allow each sub-generator to learn the distribution of the video at different levels of resolution. We also need only a few GPUs to train a highly complex generator that far outperforms the predecessor in terms of inception scores.

中文翻译：

---

稀疏训练，密集生成：高分辨率时间 GAN 的内存高效无监督训练

由于数据集的庞大规模和每次观察的复杂性，在视频数据集上训练生成对抗网络 (GAN) 是一项挑战。一般来说，训练 GAN 的计算成本随分辨率呈指数增长。在这项研究中，我们提出了一种新的内存高效的高分辨率视频数据集无监督学习方法，其计算成本仅与分辨率成线性关系。我们通过将生成器模型设计为一堆小型子生成器并以特定方式训练模型来实现这一点。我们用自己特定的鉴别器训练每个子生成器。在训练时，我们在每对连续子生成器之间引入一个辅助子采样层，将帧率降低一定比例。这个过程可以允许每个子生成器学习不同分辨率级别的视频分布。我们还只需要几个 GPU 来训练一个高度复杂的生成器，它在初始分数方面远远优于前辈。