论文标题
部分可观测时空混沌系统的无模型预测
FewGAN: Generating from the Joint Distribution of a Few Images
论文作者
论文摘要
我们介绍了很少的gan，这是一种生成模型，用于生成新颖，高质量和多样的图像，其贴片分布在于少数N> 1个训练样本的关节贴片分布。从本质上讲，该方法是一种分层贴片，它以与VQ-GAN相似的方式进行了第一个粗尺度的量化，其次是在更精细的尺度上的残留全卷积gan的金字塔。我们的关键想法是首先使用量化来学习固定的补丁嵌入以进行训练图像。然后，我们使用一组单独的侧面图像来对生成图像的结构进行建模，该模型在训练图像的学习贴片嵌入方式上训练。在最高量表上使用量化可以使模型同时生成条件和无条件的新型图像。随后，补丁程序可提供细节，从而产生高质量的图像。在一系列广泛的实验中，表明很少有数量和定性优于基础。
We introduce FewGAN, a generative model for generating novel, high-quality and diverse images whose patch distribution lies in the joint patch distribution of a small number of N>1 training samples. The method is, in essence, a hierarchical patch-GAN that applies quantization at the first coarse scale, in a similar fashion to VQ-GAN, followed by a pyramid of residual fully convolutional GANs at finer scales. Our key idea is to first use quantization to learn a fixed set of patch embeddings for training images. We then use a separate set of side images to model the structure of generated images using an autoregressive model trained on the learned patch embeddings of training images. Using quantization at the coarsest scale allows the model to generate both conditional and unconditional novel images. Subsequently, a patch-GAN renders the fine details, resulting in high-quality images. In an extensive set of experiments, it is shown that FewGAN outperforms baselines both quantitatively and qualitatively.
