公开(公告)号：US20230148384A1

公开(公告)日：2023-05-11

申请号：US17524480

申请日：2021-11-11

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Wentao LIU ,  Seyed Mehdi AYYOUBZADEH ,  Yuanhao YU ,  Irina KEZELE ,  Yang WANG ,  Xiaolin WU ,  Jin TANG

IPC: G06T7/246 ,  G06N20/00

CPC classification number: G06T7/248 ,  G06N20/00 ,  G06T2207/20081 ,  G06T2207/10016

Abstract: There is provided a method, apparatus and system for adapting a machine learning model for optical flow prediction. A machine learning model can be trained or adapted based on compressed video data, using motion vector information extracted from the compressed video data as ground-truth information for use in adapting the model to a motion vector prediction task. The model so adapted can accordingly be adapted for the similar task of optical flow prediction. Thus, the model can be adapted at test time to image data which is taken from an appropriate distribution. A meta-learning process can be performed prior to such model adaptation to potentially improve the model's performance.