BriefGPT.xyz
Nov, 2023
利用共享表示优化去噪扩散概率模型
Improving Denoising Diffusion Probabilistic Models via Exploiting Shared Representations
HTML
PDF
Delaram Pirhayatifard, Mohammad Taha Toghani, Guha Balakrishnan, César A. Uribe
TL;DR
本研究提出一种名为SR-DDPM的新方法，通过利用少样本表示学习技术，解决面临有限数据的多任务图像生成挑战，以提高图像质量，并在标准图像数据集上对其进行评估，发现其在FID和SSIM指标上优于无条件和有条件的DDPM。
Abstract
In this work, we address the challenge of
multi-task image generation
with limited data for
denoising diffusion probabilistic models
(DDPM), a class of generative models that produce high-quality images by revers
→