Loss Functions of Generative Adversarial Networks (GANs): Opportunities and Challenges

被引：45
|
作者：
Pan, Zhaoqing [1 ,2 ]
Yu, Weijie [1 ]
Wang, Bosi [1 ]
Xie, Haoran [3 ]
Sheng, Victor S. [4 ]
Lei, Jianjun [5 ]
Kwong, Sam [6 ]
机构：
[1] Nanjing Univ Informat Sci & Technol, Sch Comp & Software, Nanjing 210044, Peoples R China
[2] Xidian Univ, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China
[3] Lingnan Univ, Dept Comp & Decis Sci, Hong Kong, Peoples R China
[4] Texas Tech Univ, Dept Comp Sci, Lubbock, TX 79409 USA
[5] Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China
[6] City Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China
来源：
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE | 2020年 / 4卷 / 04期
关键词：
Loss functions; generative adversarial networks (GANs); deep learning; machine learning; computational intelligence; IMAGE; DISTANCE;
D O I：
10.1109/TETCI.2020.2991774
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Recently, the Generative Adversarial Networks (GANs) are fast becoming a key promising research direction in computational intelligence. To improve the modeling ability of GANs, loss functions are used to measure the differences between samples generated by the model and real samples, and make the model learn towards the goal. In this paper, we perform a survey for the loss functions used in GANs, and analyze the pros and cons of these loss functions. Firstly, the basic theory of GANs, and its training mechanism are introduced. Then, the loss functions used in GANs are summarized, including not only the objective functions of GANs, but also the application-oriented GANs' loss functions. Thirdly, the experiments and analyses of representative loss functions are discussed. Finally, several suggestions on how to choose appropriate loss functions in a specific task are given.
引用
收藏
页码：500 / 522
页数：23
相关论文
共 50 条
  • [31] What are GANs?: Introducing Generative Adversarial Networks to Middle School Students
    Ali, Safinah
    DiPaola, Daniella
    Breazeal, Cynthia
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 15472 - 15479
  • [32] GIU-GANs: Global Information Utilization for Generative Adversarial Networks
    Tian, Yongqi
    Gong, Xueyuan
    Tang, Jialin
    Su, Binghua
    Liu, Xiaoxiang
    Zhang, Xinyuan
    NEURAL NETWORKS, 2022, 152 : 487 - 498
  • [33] Spectrum of Advancements and Developments in Multidisciplinary Domains for Generative Adversarial Networks (GANs)
    Syed Khurram Jah Rizvi
    Muhammad Ajmal Azad
    Muhammad Moazam Fraz
    Archives of Computational Methods in Engineering, 2021, 28 : 4503 - 4521
  • [34] Generative adversarial networks (GANs): Introduction, Taxonomy, Variants, Limitations, and Applications
    Sharma P.
    Kumar M.
    Sharma H.K.
    Biju S.M.
    Multimedia Tools and Applications, 2024, 83 (41) : 88811 - 88858
  • [35] Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP
    Rodrigues, Thiago Serafim
    Pinheiro, Placido Rogerio
    IEEE ACCESS, 2025, 13 : 770 - 788
  • [36] Distributionally robust chance constrained programming with generative adversarial networks (GANs)
    Zhao, Shipu
    You, Fengqi
    AICHE JOURNAL, 2020, 66 (06)
  • [37] Generic image application using GANs (Generative Adversarial Networks): A Review
    S. P. Porkodi
    V. Sarada
    Vivek Maik
    K. Gurushankar
    Evolving Systems, 2023, 14 : 903 - 917
  • [38] Breast Thermographic Image Augmentation Using Generative Adversarial Networks (GANs)
    Vivanco Gualan, Ramiro Israel
    Jimenez Gaona, Yuliana del Cisne
    Castillo Malla, Darwin Patricio
    Rodriguez-Alvarez, Maria Jose
    Lakshminarayanan, Vasudevan
    INFORMATION AND COMMUNICATION TECHNOLOGIES, TICEC 2024, 2025, 2273 : 86 - 99
  • [39] Utilization of generative adversarial networks (GANs) in the replication and restoration of calligraphy art
    Zhu, Xiaojun
    MCB Molecular and Cellular Biomechanics, 2024, 21 (03):
  • [40] Artificial gamma ray spectra simulation using Generative Adversarial Networks (GANs) and Supervised Generative Networks (SGNs)
    de Oliveira, Felipe M. F.
    Daniel, G.
    Limousin, O.
    NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2023, 1047
12345