公开(公告)号：US20230290126A1

公开(公告)日：2023-09-14

申请号：US18115059

申请日：2023-02-28

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Pengyuan LV ,  Sen FAN ,  Chengquan ZHANG ,  Kun YAO ,  Junyu HAN ,  Jingtuo LIU ,  Errui DING ,  Jingdong WANG

IPC: G06V10/774 ,  G06V10/77 ,  G06V10/42 ,  G06V10/44 ,  G06V10/25

CPC classification number: G06V10/7747 ,  G06V10/25 ,  G06V10/42 ,  G06V10/44 ,  G06V10/7715 ,  G06V30/148

Abstract: Provided are a method for training a region of interest (ROI) detection model, a method for detecting an ROI, a device, and a medium. The specific implementation includes: performing feature extraction on a sample image to obtain a sample feature data; performing non-linear mapping on the sample feature data to obtain a first feature data and a second feature data; determining an inter-region difference data according to the second feature data and a third feature data of the first feature data in a region associated with a label ROI; and adjusting at least one of a to-be-trained feature extraction parameter and a to-be-trained feature enhancement parameter of the ROI detection model according to the inter-region difference data and the region associated with the label ROI.