论文标题
使用离散内容表示形式生成的几个图像生成
Few-shot Image Generation Using Discrete Content Representation
论文作者
论文摘要
很少有图像生成和几张相关的图像翻译是两个相关的任务，这两个任务旨在为只有几张图像的看不见类别生成新图像。在这项工作中，我们首次尝试将几张图像翻译方法调整为几乎没有图像生成任务。几乎没有图像翻译将图像分解为样式向量和内容图。看不见的样式矢量可以与不同的可见内容图相结合，以产生不同的图像。但是，它需要存储可见的图像以提供内容图，并且看不见的矢量可能与可见的内容图不兼容。为了使其适应少量图像生成任务，我们通过将连续内容映射量化为离散的内容映射而不是存储可见的图像，从而学习了局部内容向量的紧凑词字典。此外，我们对根据样式向量的条件进行离散内容图的自回归分布进行建模，这可以减轻内容映射和样式向量之间的不兼容。三个真实数据集的定性和定量结果表明，与以前的方法相比，我们的模型可以为看不见的类别产生更高的多样性和忠诚度图像。
Few-shot image generation and few-shot image translation are two related tasks, both of which aim to generate new images for an unseen category with only a few images. In this work, we make the first attempt to adapt few-shot image translation method to few-shot image generation task. Few-shot image translation disentangles an image into style vector and content map. An unseen style vector can be combined with different seen content maps to produce different images. However, it needs to store seen images to provide content maps and the unseen style vector may be incompatible with seen content maps. To adapt it to few-shot image generation task, we learn a compact dictionary of local content vectors via quantizing continuous content maps into discrete content maps instead of storing seen images. Furthermore, we model the autoregressive distribution of discrete content map conditioned on style vector, which can alleviate the incompatibility between content map and style vector. Qualitative and quantitative results on three real datasets demonstrate that our model can produce images of higher diversity and fidelity for unseen categories than previous methods.
