.png){kind=icon}
.png){kind=icon}
Return
Solving the reconstruction-generation trade-off: Generative model with implicit embedding learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2023.126428.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Variational Autoencoder (VAE) and Generative adversarial network (GAN) are two classic generative models that generate realistic data from a predefined prior distribution, such as a Gaussian distribution. One advantage of VAE over GAN is its ability to simultaneously generate high-dimensional data and learn latent representations that are useful for data manipulation. However, it has been observed that a tradeoff exists between reconstruction and generation in VAE, as matching the prior distribution for the latent representations may destroy the geometric structure of the data manifold. To address this issue, we propose an autoencoder-based generative model that allows the prior to learn the embedding distribution, rather than imposing the latent variables to fit the prior. To preserve the geometric structure of the data manifold to the maximum, the embedding distribution is trained using a simple regularized autoencoder architecture. Then an adversarial strategy is employed to achieve a latent mapping. We provide both theoretical and experimental support for the effectiveness of our method, which eliminates the contradiction between preserving the geometric structure of the data manifold and matching the distribution in latent space. The code is available at https://github.com/gengcong940126/GMIEL. & COPY; 2023 Elsevier B.V. All rights reserved.
Keywords:
Autoencoder
Generative model
Embedding learning
Latent mapping
Adversarial