Title:
MODEL TRAINING METHOD AND APPARATUS, IMAGE RECOGNITION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/244425
Kind Code:
A1
Abstract:
Provided are a model training method and apparatus, an image recognition method and apparatus, an electronic device, and a storage medium, which relate to the technical field of image recognition. In the present application, the model training method comprises: firstly, performing classification processing on image features by means of an image classification layer in a neural network model, so as to obtain a classification result, wherein the image features are obtained by means of processing a sample image on the basis of a feature extraction layer of the neural network model; secondly, performing reconstruction processing on the image features by means of an image reconstruction layer in the neural network model, so as to obtain a reconstructed image; then, performing loss determination processing on the reconstructed image by means of a loss determination layer in the neural network model, so as to obtain a reconstruction loss, and then performing loss determination processing on the classification result to obtain a classification loss; and finally, performing update processing on the neural network model on the basis of the reconstruction loss and the classification loss, so as to obtain an image recognition model. By means of the method, the problem of the recognition precision of a trained image recognition model in the related art not being high can be solved.
Inventors:
HUANG YING (CN)
QIU SHANGFENG (CN)
ZHANG WENWEI (CN)
QIU SHANGFENG (CN)
ZHANG WENWEI (CN)
Application Number:
PCT/CN2021/096763
Publication Date:
December 09, 2021
Filing Date:
May 28, 2021
Export Citation:
Assignee:
GUANGZHOU HUYA TECH CO LTD (CN)
International Classes:
G06K9/00
Foreign References:
| CN111639607A | 2020-09-08 | |||
| CN110490878A | 2019-11-22 | |||
| CN107180248A | 2017-09-19 | |||
| US10529318B2 | 2020-01-07 |
Other References:
ROBERT THOMAS; THOME NICOLAS; CORD MATTHIEU: "HybridNet: Classification and Reconstruction Cooperation for Semi-supervised Learning", vol. 11211 Chap.10, no. 558, 6 October 2018 (2018-10-06), Berlin, Heidelberg , pages 158 - 175, XP047488230, ISBN: 3540745491, DOI: 10.1007/978-3-030-01234-2_10
Attorney, Agent or Firm:
CHOFN INTELLECTUAL PROPERTY (CN)
Download PDF:
Previous Patent: HEAD WORD EXTRACTION METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM
Next Patent: BALANCED FALLING MECHANISM AND GRAVIMETER
Next Patent: BALANCED FALLING MECHANISM AND GRAVIMETER