scholarly journals Enhanced Unsupervised Image Generation using GAN based Convolutional Nets

2020 ◽  
Vol 8 (6) ◽  
pp. 5312-5316
Keyword(s):  
Image Processing ◽  
Neural Nets ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Quality Model ◽  
High Quality ◽  
Style Transfer ◽  
Adversarial Networks ◽  
Generative Modeling ◽  
Result Analysis

Generative Adversarial Networks (GANs) use deep learning methods like neural nets for generative modeling. Neural style transferring of images and facial character generation of anime images are previously implemented by applying GAN methods but were not successful in giving a promising output. In this work, Image Processing is applied on the datasets in the mode along with the training of GAN system. The problem of applying GAN to generate specific images is addressed by using a clean and problem specific dataset for anime facial character generation. Modeling is done by applying Convolutional Neural Nets, GANs empirically. Neural style transfer, Automatic Anime characters are generated with high-resolution, and this model tackles the limitations by progressively increasing the resolution of both generated images and structural conditions during training. This model can be used to develop unique anime characters or the image generated can be used as inspiration by artists and graphic designers, can be used as filters in famous apps such as snapchat for style transferring. With different evaluations and result analysis, it is observed that this model is a stable and high-quality model.

Quantum generative adversarial networks for learning and loading quantum image in noisy environment

2021 ◽  
pp. 2150360
Author(s):  
Wanghao Ren ◽  
Zhiming Li ◽  
Yiming Huang ◽  
Runqiu Guo ◽  
Lansheng Feng ◽  
...  
Keyword(s):  
Image Processing ◽  
Quantum Circuit ◽  
Quantum Image Processing ◽  
Quantum Circuits ◽  
Generative Adversarial Networks ◽  
Channel Noise ◽  
Quantum Image ◽  
Adversarial Networks ◽  
Potential Applications ◽  
Classical Image

Quantum machine learning is expected to be one of the potential applications that can be realized in the near future. Finding potential applications for it has become one of the hot topics in the quantum computing community. With the increase of digital image processing, researchers try to use quantum image processing instead of classical image processing to improve the ability of image processing. Inspired by previous studies on the adversarial quantum circuit learning, we introduce a quantum generative adversarial framework for loading and learning a quantum image. In this paper, we extend quantum generative adversarial networks to the quantum image processing field and show how to learning and loading an classical image using quantum circuits. By reducing quantum gates without gradient changes, we reduced the number of basic quantum building block from 15 to 13. Our framework effectively generates pure state subject to bit flip, bit phase flip, phase flip, and depolarizing channel noise. We numerically simulate the loading and learning of classical images on the MINST database and CIFAR-10 database. In the quantum image processing field, our framework can be used to learn a quantum image as a subroutine of other quantum circuits. Through numerical simulation, our method can still quickly converge under the influence of a variety of noises.

scholarly journals Fractional Wavelet-Based Generative Scattering Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Jiasong Wu ◽  
Xiang Qiu ◽  
Jing Zhang ◽  
Fuzhi Wu ◽  
Youyong Kong ◽  
...  
Keyword(s):  
Dimensionality Reduction ◽  
Reduction Method ◽  
Gaussian White Noise ◽  
Principal Component ◽  
Experimental Results ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Adversarial Networks ◽  
Dimensionality Reduction Method

Generative adversarial networks and variational autoencoders (VAEs) provide impressive image generation from Gaussian white noise, but both are difficult to train, since they need a generator (or encoder) and a discriminator (or decoder) to be trained simultaneously, which can easily lead to unstable training. To solve or alleviate these synchronous training problems of generative adversarial networks (GANs) and VAEs, researchers recently proposed generative scattering networks (GSNs), which use wavelet scattering networks (ScatNets) as the encoder to obtain features (or ScatNet embeddings) and convolutional neural networks (CNNs) as the decoder to generate an image. The advantage of GSNs is that the parameters of ScatNets do not need to be learned, while the disadvantage of GSNs is that their ability to obtain representations of ScatNets is slightly weaker than that of CNNs. In addition, the dimensionality reduction method of principal component analysis (PCA) can easily lead to overfitting in the training of GSNs and, therefore, affect the quality of generated images in the testing process. To further improve the quality of generated images while keeping the advantages of GSNs, this study proposes generative fractional scattering networks (GFRSNs), which use more expressive fractional wavelet scattering networks (FrScatNets), instead of ScatNets as the encoder to obtain features (or FrScatNet embeddings) and use similar CNNs of GSNs as the decoder to generate an image. Additionally, this study develops a new dimensionality reduction method named feature-map fusion (FMF) instead of performing PCA to better retain the information of FrScatNets,; it also discusses the effect of image fusion on the quality of the generated image. The experimental results obtained on the CIFAR-10 and CelebA datasets show that the proposed GFRSNs can lead to better generated images than the original GSNs on testing datasets. The experimental results of the proposed GFRSNs with deep convolutional GAN (DCGAN), progressive GAN (PGAN), and CycleGAN are also given.

The Frontiers of Deep Learning for Earth System Modelling 

2021 ◽  
Author(s):  
David Hall
Keyword(s):  
Artificial Intelligence ◽  
Bias Correction ◽  
Neural Nets ◽  
Generative Adversarial Networks ◽  
System Modelling ◽  
Earth System ◽  
Adversarial Networks ◽  
The Earth ◽  
Medium Range ◽  
Earth System Modelling

<p>This talk gives an overview of cutting-edge artificial intelligence applications and techniques for the earth-system sciences. We survey the most important recent contributions in areas including extreme weather, physics emulation, nowcasting, medium-range forecasting, uncertainty quantification, bias-correction, generative adversarial networks, data in-painting, network-HPC coupling, physics-informed neural nets, and geoengineering, amongst others. Then, we describe recent AI breakthroughs that have the potential to be of greatest benefit to the geosciences. We also discuss major open challenges in AI for science and their potential solutions. This talk is a living document, in that it is updated frequently, in order to accurately relect this rapidly changing field.</p>

scholarly journals Parkinson’s Disease EMG Data Augmentation and Simulation with DCGANs and Style Transfer

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2605 ◽  
Author(s):  
Rafael Anicet Zanini ◽  
Esther Luna Colombini
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Data Augmentation ◽  
Experimental Results ◽  
Generative Adversarial Networks ◽  
Style Transfer ◽  
Treatment Approaches ◽  
Adversarial Networks

This paper proposes two new data augmentation approaches based on Deep Convolutional Generative Adversarial Networks (DCGANs) and Style Transfer for augmenting Parkinson’s Disease (PD) electromyography (EMG) signals. The experimental results indicate that the proposed models can adapt to different frequencies and amplitudes of tremor, simulating each patient’s tremor patterns and extending them to different sets of movement protocols. Therefore, one could use these models for extending the existing patient dataset and generating tremor simulations for validating treatment approaches on different movement scenarios.

Sign in / Sign up

Export Citation Format

Share Document