Deformable convolution method and device and storable medium

The invention discloses a deformable convolution method and device and a storage medium. The deformable convolution method comprises the following steps of 1, performing conventional convolution on an input feature map to obtain offset vectors of multiple groups of sampling point coordinates; 2, ext...

Full description

Saved in:
Bibliographic Details
Main Authors HUANG JIANWU, CAO YANG, CHENG XIAOLONG, LU TONG
Format Patent
LanguageChinese
English
Published 05.07.2022
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:The invention discloses a deformable convolution method and device and a storage medium. The deformable convolution method comprises the following steps of 1, performing conventional convolution on an input feature map to obtain offset vectors of multiple groups of sampling point coordinates; 2, extracting the features of the shifted sampling points from the input feature map for the coordinates of each group of sampling points, and performing weighted summation by using a convolution kernel to obtain the output features of each group; and step 3, averaging the convolution output features of each group to obtain a final output feature. According to the method, through multiple groups of sampling points, the expression capability of deformable convolution is enhanced, the position consistency of channels of convolution input features is ensured, and experiments on a target detection data set COCO prove that the target detection performance is effectively improved. 本发明公开了一种可变形卷积方法、装置及存储介质,其中可变形卷积方法包括如下步骤:步骤1,对输
Bibliography:Application Number: CN202210270639