公开(公告)号：US20240104392A1

公开(公告)日：2024-03-28

申请号：US18351945

申请日：2023-07-13

Applicant: Korea Advanced Institute of Science and Technology

Inventor： JongChul YE ,  Sangjoon PARK

IPC: G06N3/098 ,  G06V10/774 ,  G06V10/94

CPC classification number: G06N3/098 ,  G06V10/7747 ,  G06V10/95

Abstract: Disclosed are a distributed learning-based multi-task vision transformer through random patch permutation and a transformation method using the same. The transformation method using the distributed learning-based multi-task vision transformer through random patch permutation may include preparing, using a task non-specific patch embedder, a patch embedding for each client and passing the patch embedding through a permutation module and then transmitting the patch embedding to a server; and storing ; by the server, the received patch embedding and using the patch embedding to update body and tail parts of a vision transformer model.