Title:
NEURAL NETWORK MODEL TRAINING METHOD, IMAGE RETRIEVAL METHOD, DEVICE, AND MEDIUM
Document Type and Number:
WIPO Patent Application WO/2023/020005
Kind Code:
A1
Abstract:
The present disclosure relates to the technical field of artificial intelligence, and in particular to the technical field of computer vision and deep learning, and provides an image retrieval method and apparatus, a device, and a medium. The present disclosure can be used in scenarios such as image processing and image recognition. The image retrieval method comprises: inputting an image to be detected into an image recognition neural network model to obtain an image feature vector output by the image recognition neural network model; and determining, on the basis of the image feature vector of the image to be detected, a first matching image set of said image from a database.
Inventors:
CHEN YUERONG (CN)
YAO KUN (CN)
SUN YIPENG (CN)
HAN JUNYU (CN)
LIU JINGTUO (CN)
YAO KUN (CN)
SUN YIPENG (CN)
HAN JUNYU (CN)
LIU JINGTUO (CN)
Application Number:
PCT/CN2022/089626
Publication Date:
February 23, 2023
Filing Date:
April 27, 2022
Export Citation:
Assignee:
BEIJING BAIDU NETCOM SCI & TECH CO LTD (CN)
International Classes:
G06F16/583; G06V10/40
Foreign References:
| CN113656582A | 2021-11-16 | |||
| CN112364195A | 2021-02-12 | |||
| CN109522967A | 2019-03-26 | |||
| CN104298749A | 2015-01-21 | |||
| CN110866140A | 2020-03-06 | |||
| CN112612913A | 2021-04-06 | |||
| US11017019B1 | 2021-05-25 |
Attorney, Agent or Firm:
BEIJING HAN KUN LAW OFFICES (CN)
Download PDF: