Patent · US Active

Image recognition network model training method, image recognition method and apparatus

US11908239B2 · kind B2 · utility

0Cited by

1References

18Claims

0Family size

Assignee

TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED · CN

Inventors

Zheng Ge · Beijing, CN
Ze Qun Jie · Lo Wu, CN
Hao Wang · 安丰镇, CN
Zhi Feng Li · Lo Wu, CN
Di Hong Gong · Lo Wu, CN
Wei Liu · Lo Wu, CN

Key dates

Filing date	May 13, 2021
Grant date	Feb 20, 2024
Priority date	—
Expiry date	Aug 26, 2042

Classification

Technology area (CPC Y)Emerging Cross-Sectional Technologies
CPC primaryY02T10/40
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

The disclosure provides an image recognition network model training method, including: acquiring a first image feature corresponding to an image set; acquiring a first identity prediction result by using an identity classifier, and acquiring a first pose prediction result by using a pose classifier; obtaining an identity classifier according to the first identity prediction result and an identity tag, and obtaining a pose classifier according to the first pose prediction result and a pose tag; performing pose transformation on the first image feature by using a generator, to obtain a second image feature corresponding to the image set; acquiring a second identity prediction result by using the identity classifier, and acquiring a second pose prediction result by using the pose classifier; and training the generator.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.