.png){kind=icon}
.png){kind=icon}
Return
Generative models with kernel distance in data space
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2022.02.053.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Generative models dealing with modeling a joint data distribution are generally autoencoder, or GAN based. Both have pros and cons, generating blurry images or being unstable in training. We propose a new generative model resembling a classical GAN transforming Gaussian noise into data space without adversarial optimization. Training of the proposed model is a two-step procedure. First, we train an autoencoder-based architecture to model a data manifold. Second, we use the Latent Trick to map Gaussian noise into the autoencoder's latent space. The resulting Latent Cramer-Wold (LCW) generator achieves competitive generative scores. Elimination of adversarial training and replacing the discriminator with kernel methods results in a stable training procedure that is not prone to mode collapse. We also show that the introduced Latent Trick can improve the generative capabilities of other latent-based models. We validate the model on standard benchmarks and compare it to different approaches. (C) 2022 Elsevier B.V. All rights reserved.
Keywords:
Deep learning
Autoencoder based model
Kernel methods
Cramer-Wold distance
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.