公开(公告)号：US11989956B2

公开(公告)日：2024-05-21

申请号：US17222879

申请日：2021-04-05

Applicant: Microsoft Technology Licensing, LLC

Inventor： Xiyang Dai ,  Yinpeng Chen ,  Bin Xiao ,  Dongdong Chen ,  Mengchen Liu ,  Lu Yuan ,  Lei Zhang

IPC: G06V20/64 ,  G02B27/01 ,  G06T3/06 ,  G06T3/40

CPC classification number: G06V20/64 ,  G02B27/0172 ,  G06T3/06 ,  G06T3/40

Abstract: Systems and methods for object detection generate a feature pyramid corresponding to image data, and rescaling the feature pyramid to a scale corresponding to a median level of the feature pyramid, wherein the rescaled feature pyramid is a four-dimensional (4D) tensor. The 4D tensor is reshaped into a three-dimensional (3D) tensor having individual perspectives including scale features, spatial features, and task features corresponding to different dimensions of the 3D tensor. The 3D tensor is used with a plurality of attention layers to update a plurality of feature maps associated with the image data. Object detection is performed on the image data using the updated plurality of feature maps.