论文标题
欧几里得空间是邪恶的：几张图像生成的双曲线属性编辑
The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation
论文作者
论文摘要
几乎没有图像生成是一项具有挑战性的任务，因为它旨在为只有几张图像的看不见类别生成各种新图像。现有的方法遭受了产生图像的质量和多样性之间的权衡。为了解决这个问题，我们提出了双曲线属性编辑〜（HAE），这是一种简单而有效的方法。与其他在欧几里得空间中起作用的方法不同，HAE使用双曲线空间中的可见类别的数据捕获图像之间的层次结构。给定经过良好训练的HAE，可以通过将给定图像的潜在代码转移到带有固定半径的Poincaré磁盘中的任何有意义的方向来生成看不见类别的图像。最重要的是，双曲线空间使我们能够通过在磁盘中设置不同的半径来控制生成的图像的语义多样性。广泛的实验和可视化表明，HAE不仅能够使用有限的数据生成具有有希望的质量和多样性的图像，而且还可以实现高度可控制且可解释的编辑过程。
Few-shot image generation is a challenging task since it aims to generate diverse new images for an unseen category with only a few images. Existing methods suffer from the trade-off between the quality and diversity of generated images. To tackle this problem, we propose Hyperbolic Attribute Editing~(HAE), a simple yet effective method. Unlike other methods that work in Euclidean space, HAE captures the hierarchy among images using data from seen categories in hyperbolic space. Given a well-trained HAE, images of unseen categories can be generated by moving the latent code of a given image toward any meaningful directions in the Poincaré disk with a fixing radius. Most importantly, the hyperbolic space allows us to control the semantic diversity of the generated images by setting different radii in the disk. Extensive experiments and visualizations demonstrate that HAE is capable of not only generating images with promising quality and diversity using limited data but achieving a highly controllable and interpretable editing process.
