Deconstructing Denoising Diffusion Models for Self-Supervised Learning

CoRR(2024)

引用 0|浏览167
暂无评分
摘要
In this study, we examine the representation learning abilities of Denoising Diffusion Models (DDM) that were originally purposed for image generation. Our philosophy is to deconstruct a DDM, gradually transforming it into a classical Denoising Autoencoder (DAE). This deconstructive procedure allows us to explore how various components of modern DDMs influence self-supervised representation learning. We observe that only a very few modern components are critical for learning good representations, while many others are nonessential. Our study ultimately arrives at an approach that is highly simplified and to a large extent resembles a classical DAE. We hope our study will rekindle interest in a family of classical methods within the realm of modern self-supervised learning.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络