Deconstructing Denoising Diffusion Models for Self-Supervised Learning

Xinlei Chen, Zhuang Liu, Saining Xie, Kaiming He

Deconstructing Denoising Diffusion Models for Self-Supervised Learning: 18 upvotes on Hugging Face Daily Papers, #7 of 14 papers on 2024-01-26. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.