DomainGallery：基于属性中心微调的少样本域驱动图像生成
DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
AI总结：
针对少样本域驱动图像生成中难以描述或未见域的问题，提出属性中心微调的DomainGallery方法，通过属性擦除、解耦、正则化与增强，在Stable Diffusion上实现优越性能。
摘要：
近年来，在大规模数据集上预训练的文生图模型取得了显著进展，使得我们只需提供描述所需内容的文本提示，就能生成各种图像。然而，当我们期望生成属于特定域（难以描述或模型未见过的域）的图像时，这些模型的可用性仍然受限。在这项工作中，我们提出了DomainGallery，一种少样本域驱动的图像生成方法，旨在以属性中心的方式对预训练的Stable Diffusion在少样本目标数据集上进行微调。具体而言，DomainGallery具有先验属性擦除、属性解耦、正则化和增强等特性。这些技术专门针对少样本域驱动生成而设计，以解决先前工作未能解决的关键问题。我们进行了大量实验，以验证DomainGallery在各种域驱动生成场景中的优越性能。代码可在https://github.com/Ldhlwh/DomainGallery获取。
英文摘要：
The recent progress in text-to-image models pretrained on large-scale datasets has enabled us to generate various images as long as we provide a text prompt describing what we want. Nevertheless, the availability of these models is still limited when we expect to generate images that fall into a specific domain either hard to describe or just unseen to the models. In this work, we propose DomainGallery, a few-shot domain-driven image generation method which aims at finetuning pretrained Stable Diffusion on few-shot target datasets in an attribute-centric manner. Specifically, DomainGallery features prior attribute erasure, attribute disentanglement, regularization and enhancement. These techniques are tailored to few-shot domain-driven generation in order to solve key issues that previous works have failed to settle. Extensive experiments are given to validate the superior performance of DomainGallery on a variety of domain-driven generation scenarios. Codes are available at https://github.com/Ldhlwh/DomainGallery.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
