Generative Model With Dynamic Linear Flow

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-th...

Full description

Bibliographic Details
Main Authors: Huadong Liao, Jiawei He, Kunxian Shu
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8869769/
Description
Summary: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 × 32 and 64 × 64 out of all flow-based methods. Additionally, DLF converges significantly faster than previous flow-based methods such as Glow.
ISSN:2169-3536