Auxiliary Conditional Generative Adversarial Networks for Image Data Set Augmentation

2018 ◽  
Author(s):  
Kalpana Devi Bai. Mudavathu ◽  
M. V. P. Chandra Sekhara Rao ◽  
K. V. Ramana
Keyword(s):  
Image Data ◽  
Generative Adversarial Networks ◽  
Data Set ◽  
Adversarial Networks

scholarly journals Cross Data Set Generalization of Ultrasound Image Augmentation using Representation Learning: A Case Study

2021 ◽  
Vol 7 (2) ◽  
pp. 755-758
Author(s):  
Daniel Wulff ◽  
Mohamad Mehdi ◽  
Floris Ernst ◽  
Jannis Hagenah
Keyword(s):  
Data Augmentation ◽  
Ultrasound Image ◽  
Image Data ◽  
Representation Learning ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Imaging Data ◽  
Data Set ◽  
Adversarial Networks ◽  
Classical Image

Abstract Data augmentation is a common method to make deep learning assessible on limited data sets. However, classical image augmentation methods result in highly unrealistic images on ultrasound data. Another approach is to utilize learning-based augmentation methods, e.g. based on variational autoencoders or generative adversarial networks. However, a large amount of data is necessary to train these models, which is typically not available in scenarios where data augmentation is needed. One solution for this problem could be a transfer of augmentation models between different medical imaging data sets. In this work, we present a qualitative study of the cross data set generalization performance of different learning-based augmentation methods for ultrasound image data. We could show that knowledge transfer is possible in ultrasound image augmentation and that the augmentation partially results in semantically meaningful transfers of structures, e.g. vessels, across domains.

scholarly journals A Novel Method for the Deblurring of Photogrammetric Images Using Conditional Generative Adversarial Networks

2020 ◽  
Vol 12 (16) ◽  
pp. 2586 ◽  
Author(s):  
Pawel Burdziakowski
Keyword(s):  
Point Clouds ◽  
Aerial Images ◽  
Generative Adversarial Networks ◽  
Camera Motion ◽  
Data Set ◽  
Adversarial Networks ◽  
Blur Kernel ◽  
Almost All ◽  
Blurred Images

The visual data acquisition from small unmanned aerial vehicles (UAVs) may encounter a situation in which blur appears on the images. Image blurring caused by camera motion during exposure significantly impacts the images interpretation quality and consequently the quality of photogrammetric products. On blurred images, it is difficult to visually locate ground control points, and the number of identified feature points decreases rapidly together with an increasing blur kernel. The nature of blur can be non-uniform, which makes it hard to forecast for traditional deblurring methods. Due to the above, the author of this publication concluded that the neural methods developed in recent years were able to eliminate blur on UAV images with an unpredictable or highly variable blur nature. In this research, a new, rapid method based on generative adversarial networks (GANs) was applied for deblurring. A data set for neural network training was developed based on real aerial images collected over the last few years. More than 20 full sets of photogrammetric products were developed, including point clouds, orthoimages and digital surface models. The sets were generated from both blurred and deblurred images using the presented method. The results presented in the publication show that the method for improving blurred photo quality significantly contributed to an improvement in the general quality of typical photogrammetric products. The geometric accuracy of the products generated from deblurred photos was maintained despite the rising blur kernel. The quality of textures and input photos was increased. This research proves that the developed method based on neural networks can be used for deblur, even in highly blurred images, and it significantly increases the final geometric quality of the photogrammetric products. In practical cases, it will be possible to implement an additional feature in the photogrammetric software, which will eliminate unwanted blur and allow one to use almost all blurred images in the modelling process.

scholarly journals MW-ACGAN: Generating Multiscale High-Resolution SAR Images for Ship Detection

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6673
Author(s):  
Lichuan Zou ◽  
Hong Zhang ◽  
Chao Wang ◽  
Fan Wu ◽  
Feng Gu
Keyword(s):  
High Resolution ◽  
Small Sample ◽  
Generative Adversarial Networks ◽  
Detection Accuracy ◽  
Data Set ◽  
Ship Detection ◽  
Multi Scale ◽  
Adversarial Networks ◽  
Sar Data ◽  
Composite Data

In high-resolution Synthetic Aperture Radar (SAR) ship detection, the number of SAR samples seriously affects the performance of the algorithms based on deep learning. In this paper, aiming at the application requirements of high-resolution ship detection in small samples, a high-resolution SAR ship detection method combining an improved sample generation network, Multiscale Wasserstein Auxiliary Classifier Generative Adversarial Networks (MW-ACGAN) and the Yolo v3 network is proposed. Firstly, the multi-scale Wasserstein distance and gradient penalty loss are used to improve the original Auxiliary Classifier Generative Adversarial Networks (ACGAN), so that the improved network can stably generate high-resolution SAR ship images. Secondly, the multi-scale loss term is added to the network, so the multi-scale image output layers are added, and multi-scale SAR ship images can be generated. Then, the original ship data set and the generated data are combined into a composite data set to train the Yolo v3 target detection network, so as to solve the problem of low detection accuracy under small sample data set. The experimental results of Gaofen-3 (GF-3) 3 m SAR data show that the MW-ACGAN network can generate multi-scale and multi-class ship slices, and the confidence level of ResNet18 is higher than that of ACGAN network, with an average score of 0.91. The detection results of Yolo v3 network model show that the detection accuracy trained by the composite data set is as high as 94%, which is far better than that trained only by the original SAR data set. These results show that our method can make the best use of the original data set, improve the accuracy of ship detection.

scholarly journals Large-Scale Distributed Training Applied to Generative Adversarial Networks for Calorimeter Simulation

2019 ◽  
Vol 214 ◽  
pp. 06025
Author(s):  
Jean-Roch Vlimant ◽  
Felice Pantaleo ◽  
Maurizio Pierini ◽  
Vladimir Loncar ◽  
Sofia Vallecorsa ◽  
...  
Keyword(s):  
Large Scale ◽  
Message Passing Interface ◽  
Scale Up ◽  
High Energy ◽  
Neural Nets ◽  
Generative Adversarial Networks ◽  
Detector Response ◽  
Data Set ◽  
Distributed Training ◽  
Adversarial Networks

In recent years, several studies have demonstrated the benefit of using deep learning to solve typical tasks related to high energy physics data taking and analysis. In particular, generative adversarial networks are a good candidate to supplement the simulation of the detector response in a collider environment. Training of neural network models has been made tractable with the improvement of optimization methods and the advent of GP-GPU well adapted to tackle the highly-parallelizable task of training neural nets. Despite these advancements, training of large models over large data sets can take days to weeks. Even more so, finding the best model architecture and settings can take many expensive trials. To get the best out of this new technology, it is important to scale up the available network-training resources and, consequently, to provide tools for optimal large-scale distributed training. In this context, our development of a new training workflow, which scales on multi-node/multi-GPU architectures with an eye to deployment on high performance computing machines is described. We describe the integration of hyper parameter optimization with a distributed training framework using Message Passing Interface, for models defined in keras [12] or pytorch [13]. We present results on the speedup of training generative adversarial networks trained on a data set composed of the energy deposition from electron, photons, charged and neutral hadrons in a fine grained digital calorimeter.

scholarly journals Is Synthetic The New Real? Performance Analysis of Time Series Generation Techniques with Focus on Network Load Forecasting

2021 ◽  
Author(s):  
Muhammad Haris Naveed ◽  
Umair Hashmi ◽  
Nayab Tajved ◽  
Neha Sultan ◽  
Ali Imran
Keyword(s):  
Synthetic Data ◽  
Real Data ◽  
Generative Adversarial Networks ◽  
Data Set ◽  
Qualitative And Quantitative ◽  
Adversarial Networks ◽  
Network Load ◽  
Quantitative Metrics ◽  
Real Performance ◽  
Analysis Of Time Series

This paper explores whether Generative Adversarial Networks (GANs) can produce realistic network load data that can be utilized to train machine learning models in lieu of real data. In this regard, we evaluate the performance of three recent GAN architectures on the Telecom Italia data set across a set of qualitative and quantitative metrics. Our results show that GAN generated synthetic data is indeed similar to real data and forecasting models trained on this data achieve similar performance to those trained on real data.

scholarly journals InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models

2020 ◽  
Vol 34 (04) ◽  
pp. 4377-4384
Author(s):  
Ameya Joshi ◽  
Minsu Cho ◽  
Viraj Shah ◽  
Balaji Pokuri ◽  
Soumik Sarkar ◽  
...  
Keyword(s):  
Image Data ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Complex Data ◽  
Challenging Problem ◽  
Two Phase ◽  
Adversarial Networks ◽  
Generative Modeling ◽  
Lack Of Control ◽  
Real World Problems

Generative Adversarial Networks (GANs), while widely successful in modeling complex data distributions, have not yet been sufficiently leveraged in scientific computing and design. Reasons for this include the lack of flexibility of GANs to represent discrete-valued image data, as well as the lack of control over physical properties of generated samples. We propose a new conditional generative modeling approach (InvNet) that efficiently enables modeling discrete-valued images, while allowing control over their parameterized geometric and statistical properties. We evaluate our approach on several synthetic and real world problems: navigating manifolds of geometric shapes with desired sizes; generation of binary two-phase materials; and the (challenging) problem of generating multi-orientation polycrystalline microstructures.

scholarly journals Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator

2020 ◽  
Vol 10 (21) ◽  
pp. 7712
Author(s):  
Ziqiang Pu ◽  
Diego Cabrera ◽  
René-Vinicio Sánchez ◽  
Mariela Cerrada ◽  
Chuan Li ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Initial Conditions ◽  
Robotic Manipulator ◽  
Learning Curves ◽  
Fault Classification ◽  
Generative Adversarial Networks ◽  
Unbalanced Data ◽  
Data Set ◽  
Adversarial Networks ◽  
Test Of Hypotheses

Data-driven machine learning techniques play an important role in fault diagnosis, safety, and maintenance of the industrial robotic manipulator. However, these methods require data that, more often that not, are hard to obtain, especially data collected from fault condition states and, without enough and appropriated (balanced) data, no acceptable performance should be expected. Generative adversarial networks (GAN) are receiving a significant interest, especially in the image analysis field due to their outstanding generative capabilities. This paper investigates whether or not GAN can be used as an oversampling tool to compensate for an unbalanced data set in an industrial manipulator fault diagnosis task. A comprehensive empirical analysis is performed taking into account six different scenarios for mitigating the unbalanced data, including classical under and oversampling (SMOTE) methods. In all of these, a wavelet packet transform is used for feature generation while a random forest is used for fault classification. Aspects such as loss functions, learning curves, random input distributions, data shuffling, and initial conditions were also considered. A non-parametric statistical test of hypotheses reveals that all GAN based fault-diagnosis outperforms both under and oversampling classical methods while, within GAN based methods, an average accuracy difference as high as 1.68% can be achieved.

scholarly journals Generative adversarial networks: a renewal for data augmentation in lung nodule classification

2019 ◽  
Author(s):  
Bruno H. L. dos Anjos ◽  
Anthony E. A. Jatobá ◽  
Marcelo C. Oliveira
Keyword(s):  
Data Augmentation ◽  
Medical Images ◽  
Lung Nodule ◽  
Pulmonary Nodules ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Data Set ◽  
Adversarial Networks ◽  
Computed Tomography Images ◽  
Large Databases

Obtaining medical images is an ethically restrictive process and still difficult to validate, depending on well-trained professional, being a laborious and time-consuming activity. Therefore, the construction of large databases of structured medical images is one of the major challenges of the deep learning applications in the computerized aid to the diagnosis in medical images. GAN presents itself as an adequate solution to supply the small number of pathological exams that compose the most diverse medical images banks. In this work we intend to develop a method using GAN to balance the data set of Computed Tomography images and improve the performance of an arbitrary classifier of pulmonary nodules. For this, two GAN architectures with the capacity to generate synthetic images of nodal cuts were trained and in a second moment, a Convolutional Neural Network was trained in rooms of different data set. The training of the different data sets were evaluated by AUC-ROC.

Sign in / Sign up

Export Citation Format

Share Document