Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SEMI-SUPERVISED REGRESSION WITH GENERATIVE ADVERSARIAL NETWORKS
Document Type and Number:
WIPO Patent Application WO/2018/209894
Kind Code:
A1
Abstract:
Method and system for performing semi-supervised regression with a generative adversarial network (GAN) that includes a generator comprising a first neural network and a discriminator comprising a second neural network, comprising: outputting, from the first neural network, generated samples derived from a random noise vector; inputting, to the second neural network, the generated samples, a plurality of labelled training samples, and a plurality of unlabelled training samples; and outputting, from the second neural network, a predicted continuous label for each of a plurality of the generated samples and unlabelled samples.

Inventors:
REZAGHOLIZADEH MEHDI (CA)
HAIDAR MD AKMAL (CA)
WU DALEI (CA)
Application Number:
PCT/CN2017/108192
Publication Date:
November 22, 2018
Filing Date:
October 28, 2017
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06K9/00; G06N3/08
Foreign References:
CN106296692A2017-01-04
CN104484682A2015-04-01
Other References:
WANG, KUNFENG ET AL.: "Generative Adversarial Networks: The State of the Art and Beyond", ACTA AUTOMATICA SINICA, vol. 43, no. 3, 31 March 2017 (2017-03-31), pages 1 - 12, XP055612268, DOI: 10.16383/j.aas.2017.y000003
GOODFELLOW, IAN J. ET AL.: "Generative Adversarial Nets", NIPS 2014, ARXIV:1406.2661, 10 June 2014 (2014-06-10), XP055549980
NASIM SOULY ET AL.: "ARXIVOFIG", 28 March 2017, CORNELL UNIVERSITY LIBRARY, article "Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network"
See also references of EP 3602392A4
Download PDF: