公开(公告)号：US20230368505A1

公开(公告)日：2023-11-16

申请号：US18361011

申请日：2023-07-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Weimian LI ,  Kaiqiang ZHU ,  Fei HUANG ,  Songcen XU

IPC: G06V10/774 ,  G06T7/12 ,  G06T3/00 ,  G06V10/40 ,  G06V10/776 ,  G06V10/74 ,  G06V10/26 ,  G06V10/762 ,  G06F40/289

CPC classification number: G06V10/774 ,  G06T7/12 ,  G06T3/0006 ,  G06V10/40 ,  G06V10/776 ,  G06V10/761 ,  G06V10/26 ,  G06V10/762 ,  G06F40/289 ,  G06T2207/20081

Abstract: This application discloses a model training method, and relates to the artificial intelligence field. The method includes: obtaining a plurality of training samples, where each training sample includes an image and a text, and the text describes a target object in the image; and inputting the plurality of training samples into a target model, so that the target model performs the following procedure until a preset stop condition is met: extracting an image feature of a first image and a text feature of a first text; obtaining a first loss value based on a difference between a first vector and a second vector, where a dimension of the first vector is the same as a dimension of the second vector; and updating the target model based on the first loss value.