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
  • [21] Semi-Supervised Learning with Generative Adversarial Networks for Pathological Speech Classification
    Trinh, Nam H.
    O'Brien, Darragh
    [J]. 2020 31ST IRISH SIGNALS AND SYSTEMS CONFERENCE (ISSC), 2020, : 214 - 218
  • [22] SEMI-SUPERVISED VARIATIONAL GENERATIVE ADVERSARIAL NETWORKS FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Wang, Hao
    Tao, Chao
    Qi, Ji
    Li, HaiFeng
    Tang, YuQi
    [J]. 2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 9792 - 9794
  • [23] Semi-supervised Multi-category Classification with Generative Adversarial Networks
    Rastogi, Reshma
    Gangnani, Ritesh
    [J]. PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PREMI 2019, PT I, 2019, 11941 : 286 - 294
  • [24] Audio-visual domain adaptation using conditional semi-supervised Generative Adversarial Networks
    Athanasiadis, Christos
    Hortal, Enrique
    Asteriadis, Stylianos
    [J]. NEUROCOMPUTING, 2020, 397 : 331 - 344
  • [25] Semi-supervised generative adversarial networks for improved colorectal polyp classification using histopathological images
    Sasmal, Pradipta
    Sharma, Vanshali
    Prakash, Allam Jaya
    Bhuyan, M. K.
    Patro, Kiran Kumar
    Samee, Nagwan Abdel
    Alamro, Hayam
    Iwahori, Yuji
    Tadeusiewicz, Ryszard
    Acharya, U. Rajendra
    Plawiak, Pawel
    [J]. INFORMATION SCIENCES, 2024, 658
  • [26] Efficient semi-supervised learning model for limited otolith data using generative adversarial networks
    El Habouz, Youssef
    El Mourabit, Yousef
    Iggane, Mbark
    El Habouz, Hammou
    Lukumon, Gafari
    Nouboud, Fathallah
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (04) : 11909 - 11922
  • [27] Poster Abstract: A Semi-Supervised Approach for Network Intrusion Detection Using Generative Adversarial Networks
    Jeong, Hyejeong
    Yu, Jieun
    Lee, Wonjun
    [J]. IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (IEEE INFOCOM WKSHPS 2021), 2021,
  • [28] Efficient semi-supervised learning model for limited otolith data using generative adversarial networks
    Youssef El Habouz
    Yousef El Mourabit
    Mbark Iggane
    Hammou El Habouz
    Gafari Lukumon
    Fathallah Nouboud
    [J]. Multimedia Tools and Applications, 2024, 83 : 11909 - 11922
  • [29] Semi-supervised generative adversarial networks for the segmentation of the left ventricle in pediatric MRI
    Decourt, Colin
    Duong, Luc
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2020, 123
  • [30] Semi-Supervised Encrypted Traffic Classification With Deep Convolutional Generative Adversarial Networks
    Iliyasu, Auwal Sani
    Deng, Huifang
    [J]. IEEE ACCESS, 2020, 8 : 118 - 126