文献类型：期刊文献

英文题名：Reinforced Neighbour Feature Fusion Object Detection with Deep Learning

作者：Wang, Ningwei[1];Li, Yaze[1];Liu, Hongzhe[1]

第一作者：Wang, Ningwei

通讯作者：Liu, HZ[1]

机构：[1]Beijing Union Univ, Coll Robot, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China

第一机构：北京联合大学机器人学院|北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, Coll Robot, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China.|[1141739]北京联合大学机器人学院;[11417]北京联合大学;[11417103]北京联合大学北京市信息服务工程重点实验室;

年份：2021

卷号：13

期号：9

外文期刊名：SYMMETRY-BASEL

收录：;Scopus(收录号：2-s2.0-85114701507);WOS:【SCI-EXPANDED(收录号:WOS:000701183100001)】；

基金：This work was supported, the National Natural Science Foundation of China (Grant No. 61871039, 62102033, 62171042, 61906017, 61802019), the Beijing Municipal Commission of Education Project (No. KM202111417001, KM201911417001), the Collaborative Innovation Center for Visual Intelligence (Grant No. CYXC2011), the Academic Research Projects of Beijing Union University(No. ZB10202003, ZK40202101, ZK120202104).

语种：英文

外文关键词：computer vision; object detection; feature extraction; region of interest; feature pyramid network

摘要：Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. However, previous works have tried to improve the performance in various object detection necks but have failed to extract features efficiently. To solve the insufficient features of objects, this work introduces some of the most advanced and representative network models based on the Faster R-CNN architecture, such as Libra R-CNN, Grid R-CNN, guided anchoring, and GRoIE. We observed the performance of Neighbour Feature Pyramid Network (NFPN) fusion, ResNet Region of Interest Feature Extraction (ResRoIE) and the Recursive Feature Pyramid (RFP) architecture at different scales of precision when these components were used in place of the corresponding original members in various networks obtained on the MS COCO dataset. Compared to the experimental results after replacing the neck and RoIE parts of these models with our Reinforced Neighbour Feature Fusion (RNFF) model, the average precision (AP) is increased by 3.2 percentage points concerning the performance of the baseline network.