The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation
This addresses the problem of generating diverse, high-quality images for unseen categories with few examples, offering a controllable and interpretable method for image editing.
The paper tackles the trade-off between quality and diversity in few-shot image generation by proposing Hyperbolic Attribute Editing (HAE), which uses hyperbolic space to capture image hierarchies and control semantic diversity, achieving promising results with limited data.
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.