Score-Based Generative Models
GPTKB entity
Statements (25)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
Generative Model
|
| gptkbp:advantage |
High Computational Cost
High Sample Quality Slow Sampling Stable Training |
| gptkbp:application |
Image Generation
Audio Generation Data Synthesis |
| gptkbp:contrastsWith |
gptkb:GANs
VAEs |
| gptkbp:field |
gptkb:Machine_Learning
gptkb:artificial_intelligence |
| https://www.w3.org/2000/01/rdf-schema#label |
Score-Based Generative Models
|
| gptkbp:introduced |
gptkb:Yang_Song
|
| gptkbp:introducedIn |
2019
|
| gptkbp:notablePublication |
Generative Modeling by Estimating Gradients of the Data Distribution (Song & Ermon, 2019)
Score-Based Generative Modeling through Stochastic Differential Equations (Song et al., 2021) |
| gptkbp:relatedTo |
gptkb:Diffusion_Models
Denoising Score Matching |
| gptkbp:trainer |
Stochastic Differential Equations
Score Matching |
| gptkbp:uses |
gptkb:Neural_Networks
Stochastic Processes |
| gptkbp:bfsParent |
gptkb:Diffusion_Models
|
| gptkbp:bfsLayer |
8
|