公开(公告)号：US20230368499A1

公开(公告)日：2023-11-16

申请号：US18318159

申请日：2023-05-16

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Young Wan LEE ,  Jong Hee KIM ,  Jin Young MOON ,  Kang Min BAE ,  Yu Seok BAE ,  Je Seok HAM

IPC: G06V10/77 ,  G06V10/82 ,  G06V10/74 ,  G06V10/42

CPC classification number: G06V10/7715 ,  G06V10/82 ,  G06V10/761 ,  G06V10/42

Abstract: The disclosure relates to a method of extracting image features based on a vision transformer, a method of performing embedding on an input image in units of patches and extracting visual features through global attention. An apparatus for extracting an image feature based on a vision transformer according to an embodiment of the disclosure includes a memory configured to store data and a processor configured to control the memory, wherein the processor is configured to perform embedding on multi-patches for an input image, extract feature maps for the embedding multi-patches, perform transformer encoding based on a neural network using the extracted feature maps, extract a feature of the input image through a final feature map extracted through the transformer encoding, and wherein the patches have different sizes.