Content deleted Content added
Adding {{pp-vandalism}} |
Undid revision 1293381602 by Diffuser202512 (talk) |
||
Line 2:
{{Machine learning|Artificial neural network}}
In [[machine learning]], '''diffusion models''', also known as '''diffusion-based generative models''' or '''score-based generative models''', are a class of [[latent variable model|latent variable]] [[generative model|generative]] models. A diffusion model consists of two major components: the forward diffusion process, and the reverse sampling process. The goal of diffusion models is to learn a [[diffusion process]] for a given dataset, such that the process can generate new elements that are distributed similarly as the original dataset. A diffusion model models data as generated by a diffusion process, whereby a new datum performs a [[Wiener process|random walk with drift]] through the space of all possible data.<ref name="song"/> A trained diffusion model can be sampled in many ways, with different efficiency and quality.
There are various equivalent formalisms, including [[Markov chain]]s, denoising diffusion probabilistic models, noise conditioned score networks, and stochastic differential equations.<ref>{{cite journal |last1=Croitoru |first1=Florinel-Alin |last2=Hondru |first2=Vlad |last3=Ionescu |first3=Radu Tudor |last4=Shah |first4=Mubarak |date=2023 |title=Diffusion Models in Vision: A Survey |journal=IEEE Transactions on Pattern Analysis and Machine Intelligence |volume=45 |issue=9 |pages=10850–10869 |arxiv=2209.04747 |doi=10.1109/TPAMI.2023.3261988 |pmid=37030794 |s2cid=252199918}}</ref> They are typically trained using [[Variational Bayesian methods|variational inference]].<ref name="ho" /> The model responsible for denoising is typically called its "[[#Choice of architecture|backbone]]". The backbone may be of any kind, but they are typically [[U-Net|U-nets]] or [[Transformer (deep learning architecture)|transformers]].
Line 310:
<math display="block">\min_{\theta} \int_0^1 \mathbb{E}_{\pi_0, \pi_1, p_t}\left [\lVert{(x_1-x_0) - v_t(x_t)}\rVert^2\right] \,\mathrm{d}t.</math>
The data pair <math>(x_0, x_1)</math> can be any coupling of <math>\pi_0</math> and <math>\pi_1</math>, typically independent (i.e., <math>(x_0,x_1) \sim \pi_0 \times \pi_1</math>) obtained by randomly combining observations from <math>\pi_0</math> and <math>\pi_1</math>. This process ensures that the trajectories closely mirror the density map of <math>x_t</math> trajectories but ''reroute'' at intersections to ensure causality.
[[File:Reflow Illustration.png|thumb|390px|The reflow process<ref name=":0"/>]]
| |||