公开(公告)号：US20240221346A1

公开(公告)日：2024-07-04

申请号：US17800880

申请日：2022-01-29

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Zhigang WANG ,  Jian WANG ,  Hao SUN ,  Errui DING

IPC: G06V10/44 ,  G06T9/00 ,  G06V10/74 ,  G06V10/762 ,  G06V10/80

CPC classification number: G06V10/44 ,  G06T9/00 ,  G06V10/761 ,  G06V10/762 ,  G06V10/806

Abstract: The present disclosure provides a model training method and apparatus, a pedestrian re-identification method and apparatus, and an electronic device, and relates to the field of artificial intelligence, and specifically to computer vision and deep learning technologies, which can be applied to smart city scenarios. A specific implementation solution is: performing, by using a first encoder, feature extraction on a first pedestrian image and a second pedestrian image in a sample dataset, to obtain an image feature of the first pedestrian image and an image feature of the second pedestrian image; fusing the image feature of the first pedestrian image and the image feature of the second pedestrian image, to obtain a fused feature; performing, by using a first decoder, feature decoding on the fused feature, to obtain a third pedestrian image; and determining the third pedestrian image as a negative sample image of the first pedestrian image, and using the first pedestrian image and the negative sample image to train a first preset model to convergence, to obtain a pedestrian re-identification model. The embodiments of the present disclosure can improve the effect of the model in distinguishing between pedestrians with similar appearances but different identities.

公开(公告)号：US20230289402A1

公开(公告)日：2023-09-14

申请号：US18055393

申请日：2022-11-14

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Jian WANG ,  Xiangbo SU ,  Qiman WU ,  Zhigang WANG ,  Hao SUN ,  Errui DING ,  Jingdong WANG ,  Tian WU ,  Haifeng WANG

IPC: G06K9/62

CPC classification number: G06K9/62 ,  G06K9/6288

Abstract: Provided are a joint perception model training method, a joint perception method, a device, and a storage medium. The joint perception model training method includes: acquiring sample images and perception tags of the sample images; acquiring a preset joint perception model, where the joint perception model includes a feature extraction network and a joint perception network; performing feature extraction on the sample images through the feature extraction network to obtain target sample features; performing joint perception through the joint perception network according to the target sample features to obtain perception prediction results; and training the preset joint perception model according to the perception prediction results and the perception tags, where the joint perception includes executing at least two perception tasks.