{"title":"Few-Shot Image Generation via Style Adaptation and Content Preservation.","authors":"Xiaosheng He, Fan Yang, Fayao Liu, Guosheng Lin","doi":"10.1109/TNNLS.2024.3477467","DOIUrl":null,"url":null,"abstract":"<p><p>Training a generative model with limited data (e.g., 10) is a very challenging task. Many works propose to fine-tune a pretrained GAN model. However, this can easily result in overfitting. In other words, they manage to adapt the style but fail to preserve the content, where style denotes the specific properties that define a domain while content denotes the domain-irrelevant information that represents diversity. Recent works try to maintain a predefined correspondence to preserve the content, however, the diversity is still not enough and it may affect style adaptation. In this work, we propose a paired image reconstruction approach for content preservation. We propose to introduce an image translation module to GAN transferring, where the module teaches the generator to separate style and content, and the generator provides training data to the translation module in return. Qualitative and quantitative experiments show that our method consistently surpasses the state-of-the-art methods in a few-shot setting.</p>","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2000,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on neural networks and learning systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/TNNLS.2024.3477467","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Training a generative model with limited data (e.g., 10) is a very challenging task. Many works propose to fine-tune a pretrained GAN model. However, this can easily result in overfitting. In other words, they manage to adapt the style but fail to preserve the content, where style denotes the specific properties that define a domain while content denotes the domain-irrelevant information that represents diversity. Recent works try to maintain a predefined correspondence to preserve the content, however, the diversity is still not enough and it may affect style adaptation. In this work, we propose a paired image reconstruction approach for content preservation. We propose to introduce an image translation module to GAN transferring, where the module teaches the generator to separate style and content, and the generator provides training data to the translation module in return. Qualitative and quantitative experiments show that our method consistently surpasses the state-of-the-art methods in a few-shot setting.
用有限的数据(例如 10 个数据)训练生成模型是一项极具挑战性的任务。许多研究都建议对预训练的 GAN 模型进行微调。然而,这很容易导致过度拟合。换句话说,它们设法调整了风格,但未能保留内容,其中风格表示定义域的特定属性,而内容表示代表多样性的与领域无关的信息。最近的研究试图通过保持预定义的对应关系来保留内容,但多样性仍然不够,而且可能会影响风格的适应性。在这项工作中,我们提出了一种配对图像重构方法来保存内容。我们建议在 GAN 传输过程中引入图像翻译模块,该模块教生成器分离风格和内容,生成器则为翻译模块提供训练数据作为回报。定性和定量实验表明,我们的方法在少量拍摄的情况下始终超越最先进的方法。
期刊介绍:
The focus of IEEE Transactions on Neural Networks and Learning Systems is to present scholarly articles discussing the theory, design, and applications of neural networks as well as other learning systems. The journal primarily highlights technical and scientific research in this domain.