公开(公告)号：US11735315B2

公开(公告)日：2023-08-22

申请号：US17213896

申请日：2021-03-26

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Binghong Wu ,  Yehui Yang ,  Yanwu Xu ,  Lei Wang

IPC: G16H30/40 ,  G06F18/25 ,  G06N3/045 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G16H50/20

CPC classification number: G16H30/40 ,  G06F18/251 ,  G06F18/253 ,  G06N3/045 ,  G06V10/764 ,  G06V10/806 ,  G06V10/82 ,  G16H50/20

Abstract: Embodiments of the present disclosure disclose a method, apparatus, and device for fusing features applied to small target detection, and a storage medium, relate to the field of computer vision technology. A particular embodiment of the method for fusing features applied to small target detection comprises: acquiring feature maps output by convolutional layers in a Backbone network; performing convolution on the feature maps to obtain input feature maps of feature layers, the feature layers representing resolutions of the input feature maps; and fusing, based on densely connection feature pyramid network features, the input feature maps of each feature layer to obtain output feature maps of the feature layer. Since no additional convolutional layer is introduced for feature fusion, the detection performance for small targets may be enhanced without additional parameters, and the detection ability for small targets may be improved with computing resource constraints.

公开(公告)号：US20210224581A1

公开(公告)日：2021-07-22

申请号：US17213896

申请日：2021-03-26

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Binghong Wu ,  Yehui Yang ,  Yanwu Xu ,  Lei Wang

IPC: G06K9/62 ,  G06N3/04

Abstract: Embodiments of the present disclosure disclose a method, apparatus, and device for fusing features applied to small target detection, and a storage medium, relate to the field of computer vision technology. A particular embodiment of the method for fusing features applied to small target detection comprises: acquiring feature maps output by convolutional layers in a Backbone network; performing convolution on the feature maps to obtain input feature maps of feature layers, the feature layers representing resolutions of the input feature maps; and fusing, based on densely connection feature pyramid network features, the input feature maps of each feature layer to obtain output feature maps of the feature layer. Since no additional convolutional layer is introduced for feature fusion, the detection performance for small targets may be enhanced without additional parameters, and the detection ability for small targets may be improved with computing resource constraints.