B-PesNet: Smoothly Propagating Semantics for Robust and Reliable Multi-Scale Object Detection for Secure Systems

作     者：Yunbo Rao Hongyu Mu Zeyu Yang Weibin Zheng Faxin Wang Jiansu Pu Shaoning Zeng 

作者机构：School of Information and Software EngineeringUniversity of Electronic Science and Technology of ChinaChengdu610054China Yangtze Delta Region Institute(Huzhou)University of Electronic Science and Technology of ChinaHuzhou313000China 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2022年第132卷第9期

页      面：1039-1054页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the Science and Technology Project of Sichuan(Nos.2019YFG0504,2021YFG0314,2020YFG0459) the National Natural Science Foundation of China(Grant Nos.61872066 and U19A2078) 

主　　题：Object detection Pre-ReLU CNN Balanced loss 

摘      要：Multi-scale object detection is a research hotspot,and it has critical applications in many secure *** the object detection algorithms have constantly been progressing recently,how to perform highly accurate and reliable multi-class object detection is still a challenging task due to the influence of many factors,such as the deformation and occlusion of the object in the actual *** more interference factors,the more complicated the semantic information,so we need a deeper network to extract deep ***,deep neural networks often suffer from network *** prevent the occurrence of degradation on deep neural networks,we put forth a new model using a newly-designed Pre-ReLU,which inserts a ReLU layer before the convolution layer for the sake of preventing network degradation and ensuring the performance of deep *** structure can transfer the semantic information more smoothly from the shallow to the deep ***,the deep networks will encounter not only degradation,but also a decline in ***,to speed up the two-stage detector,we divide the feature map into many groups so as to diminish the number of ***,calculation speed has been enhanced,achieving a balance between speed and *** mathematical demonstration,a Balanced Loss(BL)is proposed by a balance factor to decrease the weight of the negative sample during the training phase to balance the positives and ***,our detector demonstrates rosy results in a range of experiments and gains an mAP of 73.38 on PASCAL VOC2007,which approaches the requirement of many security systems.