公开(公告)号：US20230079275A1

公开(公告)日：2023-03-16

申请号：US17985000

申请日：2022-11-10

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

Inventor： Tianyi Wu ,  Yu Zhu ,  Guodong Guo

IPC: G06V20/40 ,  G06V10/26 ,  G06V10/75 ,  G06V10/62

Abstract: The present disclosure provides a method and apparatus for training a semantic segmentation model and a method and apparatus for performing a semantic segmentation on a video. The method comprises: acquiring a training sample set, wherein a training sample in the training sample set comprises at least one sample video stream and a pixel-level annotation result of the sample video stream; modeling a spatiotemporal context between video frames in the sample video stream using an initial semantic segmentation model to obtain a context representation of the sample video stream; calculating a temporal contrastive loss based on the context representation of the sample video stream and the pixel-level annotation result of the sample video stream; and updating a parameter of the initial semantic segmentation model based on the temporal contrastive loss to obtain a trained semantic segmentation model.

公开(公告)号：US20230046088A1

公开(公告)日：2023-02-16

申请号：US17975874

申请日：2022-10-28

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

Inventor： Tianyi Wu ,  Yu Zhu ,  Guodong Guo

IPC: G06V10/77 ,  G06V10/774

Abstract: Disclosed are a method for training a Student Network and a method for recognizing an image. The method includes: acquiring first prediction feature information of a sample image on the first granularity and second prediction feature information of the sample image on the second granularity by inputting the sample image into a Student Network, and acquiring first feature information of the sample image on the first granularity and second feature information of the sample image on the second granularity by inputting the sample image into a Teacher Network, and acquiring a target Student Network.