RDCGAN: Unsupervised Representation Learning With Regularized Deep Convolutional Generative Adversarial Networks

机译：RDCGAN：具有正则化深度卷积生成对抗网络的无监督表示学习

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

In Recent years, Representation learning as one of the information extraction and data mapping methods in machine learning systems has received huge attention. Artificial deep neural networks are considered as one of the basic structures capable of representation learning. However, a large number of standard representation learning methods are supervised and requires a lot of labeled data. In this paper, we introduce an unsupervised representation learning by designing and implementing deep neural networks (DNNs) in combination with Generative Adversarial Networks (GANs). The main idea behind the proposed method, which causes the superiority of this method over others is representation learning via the generative models and encoder networks altogether. In this research, encoders are utilized in addition to the generative models to help the more features to be extracted. It is shown that the proposed method not only help feature extraction but accelerate and improve the performance of the learning in GANs which lead to better feature extraction. The results confirm the superiority of the proposed approach regarding classification accuracy by 2% to 6% improvement over other unsupervised feature learning methods.

机译：近年来，表示学习作为机器学习系统中的一种信息提取和数据映射方法，受到了广泛的关注。人工深度神经网络被认为是能够代表学习的基本结构之一。但是，有许多标准表示学习方法受到监督，并且需要大量标记数据。在本文中，我们通过设计和实现深度神经网络（DNN）以及生成对抗网络（GAN）来介绍无监督的表示学习。提出的方法背后的主要思想是通过生成模型和编码器网络进行表示学习，从而使该方法优于其他方法。在这项研究中，除了生成模型外，还使用编码器来帮助提取更多特征。结果表明，所提出的方法不仅有助于特征提取，而且可以加速和提高GAN中学习的性能，从而导致更好的特征提取。结果证实，与其他无监督特征学习方法相比，该方法在分类精度方面的优势提高了2％至6％。

著录项

来源
《Conference on Artificial Intelligence and Robotics;Asia-Pacific International Symposium》|2018年|31-38|共8页
会议地点 Kish Island(IR)
作者
Mehran Mehralian; Babak Karasfi;
展开▼
作者单位

Islamic Azad University Qazvin Iran;

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Feature extraction; Generators; Training; Generative adversarial networks; Image reconstruction; Image classification; Gallium nitride;

机译：特征提取;发电机；训练;生成对抗网络；影像重建;图像分类；氮化镓;

相似文献

外文文献
中文文献
专利

1. Local and non-local dependency learning and emergence of rule-like representations in speech data by deep convolutional generative adversarial networks [J] . Gasper Begus Computer speech and language . 2022,第Jana期

机译：深度卷积生成对冲网络，局部和非本地依赖学习和语音数据中的规则样式的出现
2. Learning Localized Representations of Point Clouds With Graph-Convolutional Generative Adversarial Networks [J] . Diego Valsesia, Giulia Fracastoro, Enrico Magli Multimedia, IEEE Transactions on . 2021,第1期

机译：用图形卷积生成的对抗网络学习点云的本地化表示
3. An improved unsupervised representation learning generative adversarial network for remote sensing image scene classification [J] . Wei Yufan, Luo Xiaobo, Hu Lixin, Remote sensing letters . 2020,第4a6期

机译：一种改进的遥感图像场景分类学习生成的逆势网络
4. RDCGAN: Unsupervised Representation Learning With Regularized Deep Convolutional Generative Adversarial Networks [C] . Mehran Mehralian, Babak Karasfi Conference on Artificial Intelligence and Robotics . 2018

机译：RDCGAN：与正规化的深度卷积生成的对抗网络学习无监督的代表性
5. Face Aging Using Deep Convolutional Generative Adversarial Network with Condition [D] . Liu, Yingzhu 2019

机译：有条件的深度卷积生成对抗网络的人脸老化
6. Automated Pulmonary Nodule Classification in Computed Tomography Images Using a Deep Convolutional Neural Network Trained by Generative Adversarial Networks [O] . Yuya Onishi, Atsushi Teramoto, Masakazu Tsujimoto, 2006

机译：使用由生成对抗网络训练的深卷积神经网络在计算机断层扫描图像中自动进行肺结节分类
7. Local and non-local dependency learning and emergence of rule-like representations in speech data by Deep Convolutional Generative Adversarial Networks [O] . Gašper Beguš 2021

机译：深度卷积生成对抗网络的语音数据中的本地和非本地依赖学习和局限性的出现

RDCGAN: Unsupervised Representation Learning With Regularized Deep Convolutional Generative Adversarial Networks

摘要

著录项

相似文献

相关主题

期刊订阅