GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue

2020-09-24 · Pirazh Khorramshahi, Hossein Souri, Rama Chellappa, Soheil Feizi

Building on the success of deep learning, Generative Adversarial Networks (GANs) provide a modern approach to learn a probability distribution from observed samples. GANs are often formulated as a zero-sum game between two sets of functions; the generator and the discriminator. Although GANs have shown great potentials in learning complex distributions such as images, they often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution. As a consequence, the diversity of generated samples is lower than that of the observed ones. To tackle this issue, we take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity. We call this approach GANs with Variational Entropy Regularizers (GAN+VER). Existing remedies for the mode collapse issue in GANs can be easily coupled with our proposed variational entropy regularization. Through extensive experimentation on standard benchmark datasets, we show all the existing evaluation metrics highlighting difference of real and generated samples are significantly improved with GAN+VER.

📄 PDF Abstract BibTeX arXiv:2009.11921

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

OptAGAN: Entropy-based finetuning on text VAE-GAN

2021-09-01 · Paolo Tirotta, Stefano Lodi

Transfer learning through large pre-trained models has changed the landscape of current applications in natural language processing (NLP). Recently Optimus, a variational autoencoder (VAE) which combines two pre-trained …

Decoder Diversity Reinforcement Learning (RL)Text Generation+1

Prescribed Generative Adversarial Networks

2019-10-09 · Adji B. Dieng, Francisco J. R. Ruiz, David M. Blei, Michalis K. Titsias

Generative adversarial networks (GANs) are a powerful approach to unsupervised learning. They have achieved state-of-the-art performance in the image domain. However, GANs are limited in two ways. They often learn distri…

Image Generation

Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs

2018-10-09 · ICLR 2019 5 · Yogesh Balaji, Hamed Hassani, Rama Chellappa, Soheil Feizi

Building on the success of deep learning, two modern approaches to learn a probability model from the data are Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs). VAEs consider an explicit probabi…

Choquet regularization for reinforcement learning

2022-08-17 · Xia Han, Ruodu Wang, Xun Yu Zhou

We propose \emph{Choquet regularizers} to measure and manage the level of exploration for reinforcement learning (RL), and reformulate the continuous-time entropy-regularized RL problem of Wang et al. (2020, JMLR, 21(198…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Label-Conditioned Next-Frame Video Generation with Neural Flows

2019-10-16 · David Donahue

Recent state-of-the-art video generation systems employ Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs) to produce novel videos. However, VAE models typically produce blurry outputs when faced w…

Video Generation