arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.04221cs.CVcs.AIcs.LGcs.NE
收藏

信噪比扩散模型的关联视角

Connective Viewpoints of Signal-to-Noise Diffusion Models

VinAI Research(VinAI研究院);Monash University(莫纳什大学)

Khanh Doan, Long Tung Vuong, Tuan Nguyen, Anh Tuan Bui, Quyen Tran, Thanh-Toan Do, Dinh Phung, Trung Le

AI总结:

本文从信噪比与信息理论关联的视角系统研究信噪比扩散模型中的噪声调度器,并提出广义反向方程以提升推理性能。

摘要:

扩散模型(DM)已成为生成模型的基础组成部分,在图像生成、音频生成和复杂数据插值等多个领域表现卓越。信噪比扩散模型构成一个多样化的家族,涵盖了大多数最先进的扩散模型。尽管已有若干研究尝试从不同视角研究信噪比(S2N)扩散模型,但仍缺乏一项连接不同观点并探索新视角的综合性研究。在本研究中,我们对噪声调度器提供了一个全面的视角,通过信噪比(SNR)的透镜及其与信息理论的联系来审视其作用。在此框架基础上,我们发展了一个广义反向方程,以提升推理过程的性能。

英文摘要:

Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpolation. Signal-to-Noise diffusion models constitute a diverse family covering most state-of-the-art diffusion models. While there have been several attempts to study Signal-to-Noise (S2N) diffusion models from various perspectives, there remains a need for a comprehensive study connecting different viewpoints and exploring new perspectives. In this study, we offer a comprehensive perspective on noise schedulers, examining their role through the lens of the signal-to-noise ratio (SNR) and its connections to information theory. Building upon this framework, we have developed a generalized backward equation to enhance the performance of the inference process.

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。

↑