Title:
NEURAL NETWORK TRAINING METHOD AND APPARATUS, AND IMAGE PROCESSING METHOD AND APPARATUS
Document Type and Number:
WIPO Patent Application WO/2020/232977
Kind Code:
A1
Abstract:
The present disclosure relates to a neural network training method and apparatus, and an image processing method and apparatus. The training method comprises: by means of a neural network, performing classification processing on target images in a training set to obtain a predicted classification result of the target images; and, on the basis of the predicted classification results and an initial category label and corrected category label of the target images, training the neural network. The embodiments of the present disclosure can supervise the training process of a neural network jointly by means of initial and corrected category labels, simplifying the training process and the network structure.
Inventors:
HAN JIANGFAN (CN)
LUO PING (CN)
WANG XIAOGANG (CN)
LUO PING (CN)
WANG XIAOGANG (CN)
Application Number:
PCT/CN2019/114470
Publication Date:
November 26, 2020
Filing Date:
October 30, 2019
Export Citation:
Assignee:
BEIJING SENSETIME TECH DEVELOPMENT CO LTD (CN)
International Classes:
G06N3/04; G06N3/08; G06V10/762; G06V10/764
Foreign References:
| CN108614858A | 2018-10-02 | |||
| CN110210535A | 2019-09-06 | |||
| CN108765340A | 2018-11-06 | |||
| CN108305296A | 2018-07-20 |
Attorney, Agent or Firm:
LINDA LIU & PARTNERS (CN)
Download PDF: