Stable Attribute Group Editing for Reliable Few-shot Image Generation

TL;DR

This paper introduces SAGE, a stable few-shot image generation method that improves category retention and downstream classification by leveraging class centers and attribute selection, addressing class inconsistency issues in GANs.

Contribution

The paper proposes SAGE, an advanced attribute editing framework that enhances class stability and downstream classification in few-shot image generation, building upon and improving previous AGE methods.

Findings

SAGE significantly improves class retention in generated images.

Enhanced downstream classification performance using pixel and frequency domain techniques.

Addresses class inconsistency in GAN-generated images for better utility.

Abstract

Few-shot image generation aims to generate data of an unseen category based on only a few samples. Apart from basic content generation, a bunch of downstream applications hopefully benefit from this task, such as low-data detection and few-shot classification. To achieve this goal, the generated images should guarantee category retention for classification beyond the visual quality and diversity. In our preliminary work, we present an ``editing-based'' framework Attribute Group Editing (AGE) for reliable few-shot image generation, which largely improves the generation performance. Nevertheless, AGE's performance on downstream classification is not as satisfactory as expected. This paper investigates the class inconsistency problem and proposes Stable Attribute Group Editing (SAGE) for more stable class-relevant image generation. SAGE takes use of all given few-shot images and estimates a class center embedding based on the category-relevant attribute dictionary. Meanwhile, according to the projection weights on the category-relevant attribute dictionary, we can select category-irrelevant attributes from the similar seen categories. Consequently, SAGE injects the whole distribution of the novel class into StyleGAN's latent space, thus largely remains the category retention and stability of the generated images. Going one step further, we find that class inconsistency is a common problem in GAN-generated images for downstream classification. Even though the generated images look photo-realistic and requires no category-relevant editing, they are usually of limited help for downstream classification. We systematically discuss this issue from both the generative model and classification model perspectives, and propose to boost the downstream classification performance of SAGE by enhancing the pixel and frequency components.