Mixture Density Generative Adversarial Networks

Eghbal-zadeh, Hamid; Zellinger, Werner; Widmer, Gerhard

doi:10.1109/cvpr.2019.00597

Cited by 32 publications

(27 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Probabilistic GAN (PGAN) which is a new kind of GAN with a modified objective function. The main idea behind this method is to integrate a probabilistic model (A Gaussian Mixture Model) into the GAN framework that supports likelihood rather than classification [236]. A GAN with Bayesian Recently, Google proposed extended versions of GANs called Boundary Equilibrium Generative Adversarial Networks (BEGAN) with a simple but robust architecture [228].…”

Section: Review On Ganmentioning

confidence: 99%

See 1 more Smart Citation

A State-of-the-Art Survey on Deep Learning Theory and Architectures

et al. 2019

View full text Add to dashboard Cite

In recent years, deep learning has garnered tremendous success in a variety of application domains. This new field of machine learning has been growing rapidly and has been applied to most traditional application domains, as well as some new areas that present more opportunities. Different methods have been proposed based on different categories of learning, including supervised, semi-supervised, and un-supervised learning. Experimental results show state-of-the-art performance using deep learning when compared to traditional machine learning approaches in the fields of image processing, computer vision, speech recognition, machine translation, art, medical imaging, medical information processing, robotics and control, bioinformatics, natural language processing, cybersecurity, and many others. This survey presents a brief survey on the advances that have occurred in the area of Deep Learning (DL), starting with the Deep Neural Network (DNN). The survey goes on to cover Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), including Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), Auto-Encoder (AE), Deep Belief Network (DBN), Generative Adversarial Network (GAN), and Deep Reinforcement Learning (DRL). Additionally, we have discussed recent developments, such as advanced variant DL techniques based on these DL approaches. This work considers most of the papers published after 2012 from when the history of deep learning began. Furthermore, DL approaches that have been explored and evaluated in different application domains are also included in this survey. We also included recently developed frameworks, SDKs, and benchmark datasets that are used for implementing and evaluating deep learning approaches. There are some surveys that have been published on DL using neural networks and a survey on Reinforcement Learning (RL). However, those papers have not discussed individual advanced techniques for training large-scale deep learning models and the recently developed method of generative models.

show abstract

Section: Review On Ganmentioning

confidence: 99%

Section: Review On Ganmentioning

confidence: 99%

A State-of-the-Art Survey on Deep Learning Theory and Architectures

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Since then, many architectures have been proposed for improving the image generation task [58]- [60]. Some architectures include layers of pooling for image resizing (Pix2Pix, cGAN), that allow eliminating information between the convolution layers [61]. For the model of artificial signal generation proposed in this paper, it was necessary to use an architecture that would allow maintaining most of the characteristics that PD signals have in time and frequency.…”

Section: Artificial Generation Of Pd Signals From Dcganmentioning

confidence: 99%

Artificial Generation of Partial Discharge Sources Through an Algorithm Based on Deep Convolutional Generative Adversarial Networks

et al. 2020

View full text Add to dashboard Cite

The measurement of partial discharges (PD) in electrical equipment or machines subjected to high voltage can be considered as one of the most important indicators when assessing the state of an insulation system. One of the main challenges in monitoring these degradation phenomena is to adequately measure a statistically significant number of signals from each of the sources acting on the asset under test. However, in industrial environments the presence of large amplitude noise sources or the simultaneous presence of multiple PD sources may limit the acquisition of the signals and therefore the final diagnosis of the equipment status may not be the most accurate. Although different procedures and separation and identification techniques have been implemented with very good results, not having a significant number of PD pulses associated with each source can limit the effectiveness of these procedures. Based on the above, this research proposes a new algorithm of artificial generation of PD based on a Deep Convolutional Generative Adversarial Networks (DCGAN) architecture which allows artificially generating different sources of PD from a small group of real PD, in order to complement those sources that during the measurement were poorly represented in terms of signals. According to the results obtained in different experiments, the temporal and spectral behavior of artificially generated PD sources proved to be similar to that of real experimentally obtained sources. INDEX TERMS Partial discharge, electrical noise sources, machine learning, spectral power clustering technique, clustering.

show abstract

“…With the goal of deceiving the discriminator, the generator tends to generate samples that the discriminator believes highly realistic [ 22 ]. During training, these generated samples often become limited to only a few modes rather than all the modes of the dataset, which leads to the mode collapse problem [ 22 , 23 , 24 ]. Many GAN variants have emerged to solve this problem.…”

Section: Introductionmentioning

confidence: 99%

“…The generative multi-adversarial network (GMAN) [ 31 ] extends GAN models to have multiple discriminators, making this model robust to mode collapse. The mixture density generative adversarial network (MD-GAN) [ 24 ] adjusts the discriminator output using a d -dimensional embedding space to improve the mode discovery. Similarly to D2GAN, Ghosh et al [ 32 ] proposed a multi-agent GAN named the message passing multi-agent generative adversarial network (MPM GAN), which tries to explore the generated sample modes more thoroughly based on message-passing between two generators.…”

Section: Introductionmentioning

confidence: 99%

Improving Multi-Agent Generative Adversarial Nets with Variational Latent Representation

Zhao

Xiao

et al. 2020

Entropy

View full text Add to dashboard Cite

Generative adversarial networks (GANs), which are a promising type of deep generative network, have recently drawn considerable attention and made impressive progress. However, GAN models suffer from the well-known problem of mode collapse. This study focuses on this challenge and introduces a new model design, called the encoded multi-agent generative adversarial network (E-MGAN), which tackles the mode collapse problem by introducing the variational latent representations learned from a variable auto-encoder (VAE) to a multi-agent GAN. The variational latent representations are extracted from training data to replace the random noise input of the general multi-agent GANs. The generator in E-MGAN employs multiple generators and is penalized by a classifier. This integration guarantees that the proposed model not only enhances the quality of generated samples but also improves the diversity of generated samples to avoid the mode collapse problem. Moreover, extensive experiments are conducted on both a synthetic dataset and two large-scale real-world datasets. The generated samples are visualized for qualitative evaluation. The inception score (IS) and Fréchet inception distance (FID) are adopted to measure the performance of the model for quantitative assessment. The results confirmed that the proposed model achieves outstanding performances compared to other state-of-the-art GAN variants.

show abstract

Mixture Density Generative Adversarial Networks

Cited by 32 publications

References 10 publications

A State-of-the-Art Survey on Deep Learning Theory and Architectures

A State-of-the-Art Survey on Deep Learning Theory and Architectures

Artificial Generation of Partial Discharge Sources Through an Algorithm Based on Deep Convolutional Generative Adversarial Networks

Improving Multi-Agent Generative Adversarial Nets with Variational Latent Representation

Contact Info

Product

Resources

About