Image generation and classification via generative adversarial networks

被引:0
|
作者
Mirabedini, Shirin [1 ]
Dastgerdi, Shadi Hejareh [2 ]
Kangavari, Mohammadreza [2 ]
AhmadiPanah, Mandi [3 ]
机构
[1] Payame Noor Univ, Dept Comp Engn, POB 19395-3697, Tehran, Iran
[2] Iran Univ Sci & Technol IUST, Dept Comp Engn, Tehran, Iran
[3] Payame Noor Univ, Dept Management, POB 19395-3697, Tehran, Iran
来源
BIOSCIENCE RESEARCH | 2020年 / 17卷 / 02期
关键词
Game theory; Generative adversarial networks; Bio image Generation; Bio Image Classification; Deep neural networks; Deep learning;
D O I
暂无
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
In recent years, bio image processing via supervised learning with convolutional neural networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. Generative adversarial networks (GANs) are an emerging technique for both semi-supervised and unsupervised learning that has made a dramatic change in the computer vision field. GANs provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving back propagation signals through a competitive process involving a pair of networks designed by game theory. GANs may be used in a variety of applications, including bio image generation, semantic image editing, style transfer, bio image super-resolution and also classification. Image classification is an issue that utilizes image processing, pattern recognition, and classification methods. We present two applications of GANs: classification, and the generation of images that humans find visually realistic. We focus on MGAN on the MNIST dataset and we apply this architecture in the form of distributed as our novelty. The proposed method experiment on the cluster with multiple machines to improve time-consuming with data distribution and removing the interaction between nodes during the training. Using the voting algorithm to increase the accuracy of classification. We prove the improvement by using T-Test. We conclude the proposed method decreases the training time and improves the accuracy by voting.
引用
收藏
页码:1356 / 1363
页数:8
相关论文
共 50 条
  • [1] Generative Adversarial Networks in Retinal Image Classification
    Mercaldo, Francesco
    Brunese, Luca
    Martinelli, Fabio
    Santone, Antonella
    Cesarelli, Mario
    APPLIED SCIENCES-BASEL, 2023, 13 (18):
  • [2] Modified generative adversarial networks for image classification
    Zhao, Zhongtang
    Li, Ruixian
    EVOLUTIONARY INTELLIGENCE, 2023, 16 (06) : 1899 - 1906
  • [3] Modified generative adversarial networks for image classification
    Zhongtang Zhao
    Ruixian Li
    Evolutionary Intelligence, 2023, 16 : 1899 - 1906
  • [4] Generative Adversarial Networks for Hyperspectral Image Classification
    Zhu, Lin
    Chen, Yushi
    Ghamisi, Pedram
    Benediktsson, Jon Atli
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (09): : 5046 - 5063
  • [5] A review on Generative Adversarial Networks for image generation
    de Souza, Vinicius Luis Trevisan
    Marques, Bruno Augusto Dorta
    Batagelo, Harlen Costa
    Gois, Joao Paulo
    COMPUTERS & GRAPHICS-UK, 2023, 114 : 13 - 25
  • [6] Review of Generative Adversarial Networks in Image Generation
    Chi, Wanle
    Choo, Yun Huoy
    Goh, Ong Sing
    JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2022, 26 (01) : 3 - 7
  • [7] Generative Adversarial Networks in Image Generation and Recognition
    Popuri, Anoushka
    Miller, John
    2023 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE, CSCI 2023, 2023, : 1294 - 1297
  • [8] Question Generation via Generative Adversarial Networks
    Liu, Dong
    Hong, Yu
    Yao, Jianmin
    Zhou, Guodong
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [9] Marker-Embedded Tactile Image Generation via Generative Adversarial Networks
    Kim, Won Dong
    Yang, Sanghoon
    Kim, Woojong
    Kim, Jeong-Jung
    Kim, Chang-Hyun
    Kim, Jung
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (08) : 4481 - 4488
  • [10] Unsupervised Image Generation with Infinite Generative Adversarial Networks
    Ying, Hui
    Wang, He
    Shao, Tianjia
    Yang, Yin
    Zhou, Kun
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 14264 - 14273