arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.12009cs.CVcs.AI

利用多模态基础模型与聚类改进风格歧义损失

Using Multimodal Foundation Models and Clustering for Improved Style Ambiguity Loss

University of Maryland, Baltimore County(马里兰大学巴尔的摩县分校)

James Baker

AI总结:

本文提出一种无需分类器或标注数据的风格歧义损失新形式,训练扩散模型以提升创造力,并在自动化人类判断指标上优于传统方法。

摘要:

教会文本到图像模型具有创造性涉及使用风格歧义损失,这需要预训练的分类器。在这项工作中,我们探索了一种新的风格歧义训练目标形式,用于近似创造力,该形式不需要训练分类器,甚至不需要标记数据集。然后,我们训练一个扩散模型以最大化风格歧义,从而赋予扩散模型创造力,并发现我们的新方法在基于人类判断的自动化指标上优于传统方法,同时仍保持创造力和新颖性。

英文摘要:

Teaching text-to-image models to be creative involves using style ambiguity loss, which requires a pretrained classifier. In this work, we explore a new form of the style ambiguity training objective, used to approximate creativity, that does not require training a classifier or even a labeled dataset. We then train a diffusion model to maximize style ambiguity to imbue the diffusion model with creativity and find our new methods improve upon the traditional method, based on automated metrics for human judgment, while still maintaining creativity and novelty.

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。

↑