arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2302.07121cs.CVcs.LG
收藏

扩散模型通用指南

Universal Guidance for Diffusion Models

University of Maryland, College Park(马里兰大学帕克分校);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);New York University(纽约大学)

Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein

摘要:

典型的扩散模型被训练为接受特定形式的条件,最常见的是文本,并且不能在没有重新训练的情况下以其他模态为条件。在这项工作中,我们提出了一个通用的指导算法,使扩散模型被控制的任意指导方式,而不需要重新训练任何使用特定的组件。我们表明,我们的算法成功地生成高质量的图像与指导功能,包括分割,人脸识别,目标检测,和分类器信号。代码可在https://github.com/arpitbansal297/Universal-Guided-Diffusion上获得。

英文摘要:

Typical diffusion models are trained to accept a particular form of conditioning, most commonly text, and cannot be conditioned on other modalities without retraining. In this work, we propose a universal guidance algorithm that enables diffusion models to be controlled by arbitrary guidance modalities without the need to retrain any use-specific components. We show that our algorithm successfully generates quality images with guidance functions including segmentation, face recognition, object detection, and classifier signals. Code is available at https://github.com/arpitbansal297/Universal-Guided-Diffusion.

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。

↑