HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation

TL;DR

HypDAE introduces a hyperbolic space-based autoencoder that captures hierarchical image relationships, enabling high-quality, diverse, and controllable few-shot image generation with improved balance between diversity and category consistency.

Contribution

It presents the first hyperbolic diffusion autoencoder for few-shot image generation, offering enhanced control over semantic diversity and hierarchical relationships.

Findings

Outperforms prior methods in diversity and quality

Provides controllable attribute adjustment via hyperbolic radii

Achieves better balance between category preservation and diversity

Abstract

Few-shot image generation aims to generate diverse and high-quality images for an unseen class given only a few examples in that class. A key challenge in this task is balancing category consistency and image diversity, which often compete with each other. Moreover, existing methods offer limited control over the attributes of newly generated images. In this work, we propose Hyperbolic Diffusion Autoencoders (HypDAE), a novel approach that operates in hyperbolic space to capture hierarchical relationships among images from seen categories. By leveraging pre-trained foundation models, HypDAE generates diverse new images for unseen categories with exceptional quality by varying stochastic subcodes or semantic codes. Most importantly, the hyperbolic representation introduces an additional degree of control over semantic diversity through the adjustment of radii within the hyperbolic disk. Extensive experiments and visualizations demonstrate that HypDAE significantly outperforms prior methods by achieving a better balance between preserving category-relevant features and promoting image diversity with limited data. Furthermore, HypDAE offers a highly controllable and interpretable generation process.