TAGE: Trustworthy Attribute Group Editing for Stable Few-shot Image Generation

TL;DR

TAGE is a novel image generation network that enables stable, attribute-controlled image editing in few-shot scenarios by leveraging a codebook and semantic cues within a Transformer framework.

Contribution

The paper introduces TAGE, a new few-shot image generation method with modules for codebook learning, attribute prediction, and semantic prompting, improving stability and control.

Findings

Achieves superior performance on Animal Faces, Flowers, and VGGFaces datasets.

Demonstrates high stability compared to existing few-shot image generation methods.

Effectively manipulates category-agnostic attributes for unseen categories.

Abstract

Generative Adversarial Networks (GANs) have emerged as a prominent research focus for image editing tasks, leveraging the powerful image generation capabilities of the GAN framework to produce remarkable results.However, prevailing approaches are contingent upon extensive training datasets and explicit supervision, presenting a significant challenge in manipulating the diverse attributes of new image classes with limited sample availability. To surmount this hurdle, we introduce TAGE, an innovative image generation network comprising three integral modules: the Codebook Learning Module (CLM), the Code Prediction Module (CPM) and the Prompt-driven Semantic Module (PSM). The CPM module delves into the semantic dimensions of category-agnostic attributes, encapsulating them within a discrete codebook. This module is predicated on the concept that images are assemblages of attributes, and thus, by editing these category-independent attributes, it is theoretically possible to generate images from unseen categories. Subsequently, the CPM module facilitates naturalistic image editing by predicting indices of category-independent attribute vectors within the codebook. Additionally, the PSM module generates semantic cues that are seamlessly integrated into the Transformer architecture of the CPM, enhancing the model's comprehension of the targeted attributes for editing. With these semantic cues, the model can generate images that accentuate desired attributes more prominently while maintaining the integrity of the original category, even with a limited number of samples. We have conducted extensive experiments utilizing the Animal Faces, Flowers, and VGGFaces datasets. The results of these experiments demonstrate that our proposed method not only achieves superior performance but also exhibits a high degree of stability when compared to other few-shot image generation techniques.