Generalizing semi-supervised generative adversarial networks to regression using feature contrasting

被引:29
|
作者
Olmschenk, Greg [1 ,2 ]
Zhu, Zhigang [1 ,2 ]
Tang, Hao [3 ]
机构
[1] CUNY City Coll, 160 Convent Ave, New York, NY 10031 USA
[2] CUNY, Grad Ctr, 365 5th Ave, New York, NY 10016 USA
[3] CUNY, Borough Manhattan Community Coll, 199 Chambers St, New York, NY 10007 USA
基金
美国国家科学基金会;
关键词
Generative adversarial learning; Age estimation; Regression;
D O I
10.1016/j.cviu.2019.06.004
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work, we generalize semi-supervised generative adversarial networks (GANs) from classification problems to regression problems. In the last few years, the importance of improving the training of neural networks using semi-supervised training has been demonstrated for classification problems. We present a novel loss function, called feature contrasting, resulting in a discriminator which can distinguish between fake and real data based on feature statistics. This method avoids potential biases and limitations of alternative approaches. The generalization of semi-supervised GANs to the regime of regression problems of opens their use to countless applications as well as providing an avenue for a deeper understanding of how GANs function. We first demonstrate the capabilities of semi-supervised regression GANs on a toy dataset which allows for a detailed understanding of how they operate in various circumstances. This toy dataset is used to provide a theoretical basis of the semi-supervised regression GAN. We then apply the semi-supervised regression GANs to a number of real-world computer vision applications: age estimation, driving steering angle prediction, and crowd counting from single images. We perform extensive tests of what accuracy can be achieved with significantly reduced annotated data. Through the combination of the theoretical example and real-world scenarios, we demonstrate how semi-supervised GANs can be generalized to regression problems.
引用
收藏
页码:1 / 12
页数:12
相关论文
共 50 条
  • [1] Semi-supervised Text Regression with Conditional Generative Adversarial Networks
    Li, Tao
    Liu, Xudong
    Su, Shihan
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2018, : 5375 - 5377
  • [2] Semi-supervised Learning Using Generative Adversarial Networks
    Chang, Chuan-Yu
    Chen, Tzu-Yang
    Chung, Pau-Choo
    [J]. 2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2018, : 892 - 896
  • [3] Semi-supervised Seizure Prediction with Generative Adversarial Networks
    Nhan Duy Truong
    Zhou, Luping
    Kavehei, Omid
    [J]. 2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2019, : 2369 - 2372
  • [4] Semi-Supervised Learning with Coevolutionary Generative Adversarial Networks
    Toutouh, Jamal
    Nalluru, Subhash
    Hemberg, Erik
    O'Reilly, Una-May
    [J]. PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, GECCO 2023, 2023, : 568 - 576
  • [5] Pulsar candidate identification using semi-supervised generative adversarial networks
    Balakrishnan, Vishnu
    Champion, David
    Barr, Ewan
    Kramer, Michael
    Sengar, Rahul
    Bailes, Matthew
    [J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2021, 505 (01) : 1180 - 1194
  • [6] Semi-supervised image attribute editing using generative adversarial networks
    Dogan, Yahya
    Keles, Hacer Yalim
    [J]. NEUROCOMPUTING, 2020, 401 : 338 - 352
  • [7] Localizing Microseismic Events Using Semi-Supervised Generative Adversarial Networks
    Feng, Qiang
    Han, Liguo
    Zhao, Binghui
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [8] REG-GAN: SEMI-SUPERVISED LEARNING BASED ON GENERATIVE ADVERSARIAL NETWORKS FOR REGRESSION
    Rezagholizadeh, Mehdi
    Haidar, Md Akmal
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 2806 - 2810
  • [9] Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks
    Lai, Wei-Sheng
    Huang, Jia-Bin
    Yang, Ming-Hsuan
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [10] Survey on Implementations of Generative Adversarial Networks for Semi-Supervised Learning
    Sajun, Ali Reza
    Zualkernan, Imran
    [J]. APPLIED SCIENCES-BASEL, 2022, 12 (03):