scholarly journals The Use of Synthetic Data to Facilitate Eye Segmentation Using Deeplabv3+

2021 ◽  
Vol 5 (3) ◽  
pp. 1-10
Author(s):  
Melih Öz ◽  
Taner Danışman ◽  
Melih Günay ◽  
Esra Zekiye Şanal ◽  
Özgür Duman ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Real Life ◽  
Synthetic Data ◽  
Limited Data ◽  
Test Set ◽  
Human Eye ◽  
Context Data ◽  
Head Positions

The human eye contains valuable information about an individual’s identity and health. Therefore, segmenting the eye into distinct regions is an essential step towards gathering this useful information precisely. The main challenges in segmenting the human eye include low light conditions, reflections on the eye, variations in the eyelid, and head positions that make an eye image hard to segment. For this reason, there is a need for deep neural networks, which are preferred due to their success in segmentation problems. However, deep neural networks need a large amount of manually annotated data to be trained. Manual annotation is a labor-intensive task, and to tackle this problem, we used data augmentation methods to improve synthetic data. In this paper, we detail the exploration of the scenario, which, with limited data, whether performance can be enhanced using similar context data with image augmentation methods. Our training and test set consists of 3D synthetic eye images generated from the UnityEyes application and manually annotated real-life eye images, respectively. We examined the effect of using synthetic eye images with the Deeplabv3+ network in different conditions using image augmentation methods on the synthetic data. According to our experiments, the network trained with processed synthetic images beside real-life images produced better mIoU results than the network, which only trained with real-life images in the Base dataset. We also observed mIoU increase in the test set we created from MICHE II competition images.

scholarly journals Redes neurais convolucionais aplicas à detecção de objetos no domínio de futebol de robôs humanoides

2021 ◽  
Author(s):  
◽  
Lucas Ribeiro de Abreu
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Critical System ◽  
Test Set ◽  
Learning Techniques ◽  
Using Data ◽  
Vision Module

The RoboCup Soccer is one of the largest initiatives in the robotics field of research. This initiative considers the soccer match as a challenge for the robots and aims to win a match between humans versus robots by the year of 2050. The vision module is a critical system for the robots because it needs to quickly locate and classify objects of interest for the robot in order to generate the next best action. This work evaluates deep neural networks for the detection of the ball and robots. For such task, five convolutional neural networks architectures were trained for the experiment using data augmentation and transfer learning techniques. The models were evaluated in a test set, yielding promising results in precision and frames per second. The best model achieved an mAP of 0.98 and 14.7 frames per second, running on CPU

Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT

2018 ◽  
Author(s):  
Alex Hernández-García ◽  
Johannes Mehrer ◽  
Nikolaus Kriegeskorte ◽  
Peter König ◽  
Tim C. Kietzmann
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation

scholarly journals Detection of activity and position of speakers by using deep neural networks and acoustic data augmentation

2019 ◽  
Vol 134 ◽  
pp. 53-65 ◽  
Author(s):  
Paolo Vecchiotti ◽  
Giovanni Pepe ◽  
Emanuele Principi ◽  
Stefano Squartini
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Acoustic Data

scholarly journals AI-driven deep CNN approach for multi-label pathology classification using chest X-Rays

2021 ◽  
Vol 7 ◽  
pp. e495
Author(s):  
Saleh Albahli ◽  
Hafiz Tayyab Rauf ◽  
Abdulelah Algosaibi ◽  
Valentina Emilia Balas
Keyword(s):  
Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Synthetic Data ◽  
X Rays ◽  
Deep Convolutional Neural Networks ◽  
Current State ◽  
Pathology Classification ◽  
Wide Range ◽  
Multi Class Classification

Artificial intelligence (AI) has played a significant role in image analysis and feature extraction, applied to detect and diagnose a wide range of chest-related diseases. Although several researchers have used current state-of-the-art approaches and have produced impressive chest-related clinical outcomes, specific techniques may not contribute many advantages if one type of disease is detected without the rest being identified. Those who tried to identify multiple chest-related diseases were ineffective due to insufficient data and the available data not being balanced. This research provides a significant contribution to the healthcare industry and the research community by proposing a synthetic data augmentation in three deep Convolutional Neural Networks (CNNs) architectures for the detection of 14 chest-related diseases. The employed models are DenseNet121, InceptionResNetV2, and ResNet152V2; after training and validation, an average ROC-AUC score of 0.80 was obtained competitive as compared to the previous models that were trained for multi-class classification to detect anomalies in x-ray images. This research illustrates how the proposed model practices state-of-the-art deep neural networks to classify 14 chest-related diseases with better accuracy.

Characterization of a carbonate geothermal reservoir using rock-physics-guided deep neural networks

2021 ◽  
Vol 40 (10) ◽  
pp. 751-758
Author(s):  
Fabien Allo ◽  
Jean-Philippe Coulon ◽  
Jean-Luc Formento ◽  
Romain Reboul ◽  
Laure Capar ◽  
...  
Keyword(s):  
Neural Networks ◽  
Seismic Data ◽  
Deep Neural Networks ◽  
Synthetic Data ◽  
Rock Physics ◽  
Seismic Inversion ◽  
Geothermal Reservoir ◽  
Rock Properties ◽  
Hybrid Techniques ◽  
Geothermal Wells

Deep neural networks (DNNs) have the potential to streamline the integration of seismic data for reservoir characterization by providing estimates of rock properties that are directly interpretable by geologists and reservoir engineers instead of elastic attributes like most standard seismic inversion methods. However, they have yet to be applied widely in the energy industry because training DNNs requires a large amount of labeled data that is rarely available. Training set augmentation, routinely used in other scientific fields such as image recognition, can address this issue and open the door to DNNs for geophysical applications. Although this approach has been explored in the past, creating realistic synthetic well and seismic data representative of the variable geology of a reservoir remains challenging. Recently introduced theory-guided techniques can help achieve this goal. A key step in these hybrid techniques is the use of theoretical rock-physics models to derive elastic pseudologs from variations of existing petrophysical logs. Rock-physics theories are already commonly relied on to generalize and extrapolate the relationship between rock and elastic properties. Therefore, they are a useful tool to generate a large catalog of alternative pseudologs representing realistic geologic variations away from the existing well locations. While not directly driven by rock physics, neural networks trained on such synthetic catalogs extract the intrinsic rock-physics relationships and are therefore capable of directly estimating rock properties from seismic amplitudes. Neural networks trained on purely synthetic data are applied to a set of 2D poststack seismic lines to characterize a geothermal reservoir located in the Dogger Formation northeast of Paris, France. The goal of the study is to determine the extent of porous and permeable layers encountered at existing geothermal wells and ultimately guide the location and design of future geothermal wells in the area.

scholarly journals Latent Multi-Task Architecture Learning

2019 ◽  
Vol 33 ◽  
pp. 4822-4829 ◽  
Author(s):  
Sebastian Ruder ◽  
Joachim Bingel ◽  
Isabelle Augenstein ◽  
Anders Søgaard
Keyword(s):  
Neural Networks ◽  
Recent Work ◽  
Deep Neural Networks ◽  
Synthetic Data ◽  
Approaches To Learning ◽  
Average Error ◽  
Task Learning ◽  
Task Architecture ◽  
Parameter Sharing

Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find (a) the layers or subspaces that benefit from sharing, (b) the appropriate amount of sharing, and (c) the appropriate relative weights of the different task losses. Recent work has addressed each of the above problems in isolation. In this work we present an approach that learns a latent multi-task architecture that jointly addresses (a)–(c). We present experiments on synthetic data and data from OntoNotes 5.0, including four different tasks and seven different domains. Our extension consistently outperforms previous approaches to learning latent architectures for multi-task problems and achieves up to 15% average error reductions over common approaches to MTL.

scholarly journals Ship-Iceberg Classification in SAR and Multispectral Satellite Images with Neural Networks

2020 ◽  
Vol 12 (15) ◽  
pp. 2353
Author(s):  
Henning Heiselberg
Keyword(s):  
Neural Networks ◽  
Satellite Images ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Neural Nets ◽  
The Arctic ◽  
Support Vector ◽  
Sar Images ◽  
Multispectral Satellite Images ◽  
The Cost

Classification of ships and icebergs in the Arctic in satellite images is an important problem. We study how to train deep neural networks for improving the discrimination of ships and icebergs in multispectral satellite images. We also analyze synthetic-aperture radar (SAR) images for comparison. The annotated datasets of ships and icebergs are collected from multispectral Sentinel-2 data and taken from the C-CORE dataset of Sentinel-1 SAR images. Convolutional Neural Networks with a range of hyperparameters are tested and optimized. Classification accuracies are considerably better for deep neural networks than for support vector machines. Deeper neural nets improve the accuracy per epoch but at the cost of longer processing time. Extending the datasets with semi-supervised data from Greenland improves the accuracy considerably whereas data augmentation by rotating and flipping the images has little effect. The resulting classification accuracies for ships and icebergs are 86% for the SAR data and 96% for the MSI data due to the better resolution and more multispectral bands. The size and quality of the datasets are essential for training the deep neural networks, and methods to improve them are discussed. The reduced false alarm rates and exploitation of multisensory data are important for Arctic search and rescue services.

Sign in / Sign up

Export Citation Format

Share Document