.png){kind=icon}
.png){kind=icon}
Return
Generative Model With Dynamic Linear Flow
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2947567.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Flow-based generative models are a family of exact log-likelihood models with tractable sampling and latent-variable inference, hence conceptually attractive for modeling complex distributions. However, flow-based models are limited by density estimation performance issues as compared to state-of-the-art autoregressive models. Autoregressive models, which also belong to the family of likelihood-based methods, however suffer from limited parallelizability. In this paper, we propose Dynamic Linear Flow (DLF), a new family of invertible transformations with partially autoregressive structure. Our method benefits from the efficient computation of flow-based methods and high density estimation performance of autoregressive methods. We demonstrate that the proposed DLF yields state-of-the-art performance on ImageNet $32\times 32$ and $64\times 64$ out of all flow-based methods. Additionally, DLF converges significantly faster than previous flow-based methods such as Glow.
Keywords:
Data models
Estimation
Computational modeling
Jacobian matrices
Training
Couplings
Hardware
Exact likelihood
generative models
invertible transformation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W