METHOD OF TRAINING MODEL, ELECTRONIC DEVICE, AND READABLE STORAGE MEDIUM

    公开(公告)号:US20220392204A1

    公开(公告)日:2022-12-08

    申请号:US17891381

    申请日:2022-08-19

    Abstract: A method of training a model, an electronic device, and a readable storage medium are provided, which relate to a field of artificial intelligence, in particular to computer vision and deep learning technologies, and specifically used in smart city and intelligent transportation scenarios. The method includes: determining a target pre-trained model; and performing an unsupervised training and/or a semi-supervised training on the target pre-trained model based on an image acquired by the target terminal, so as to obtain a first target trained model.

    IMAGE-BASED VEHICLE DAMAGE ASSESSMENT METHOD, APPARATUS AND STORAGE MEDIUM

    公开(公告)号:US20240013364A1

    公开(公告)日:2024-01-11

    申请号:US18003992

    申请日:2022-01-29

    Abstract: An image-based vehicle damage assessment method includes: obtaining an image to be assessed of a damaged vehicle; outputting a first damage assessment box and first damage information based on the image to be assessed; in response to a first box selection operation on the image to be assessed, determining and outputting a second damage assessment box and second damage information corresponding to the first box selection operation, in which a vehicle damage image indicated by the second damage assessment box is different from the vehicle damage image indicated by the first damage assessment box, and the second damage information is vehicle damage information of the vehicle damage image indicated by the second damage assessment box.

Patent Agency Ranking