现代电子技术2024，Vol.47Issue(7)：8-16,9.DOI:10.16652/j.issn.1004-373x.2024.07.002
多头自注意力机制的Faster R-CNN目标检测算法
Faster R-CNN object detection algorithm based on multi-head self-attention mechanism
摘要
Abstract
A faster R-CNN object detection algorithm that integrates multi-head attention mechanism,ROI(region of interest)align and soft-NMS(non maximum suppression)is proposed.This algorithm aims to improve the detection accuracy and eliminate the missed detections and false detections in the original faster R-CNN object detection network.In order to improve the percep-tion ability of faster R-CNN to extract important features from feature maps and reduce the extraction of irrelevant features,an at-tention mechanism is embedded in the network.In response to the dimensionality reduction operation of the shared fully-con-nected layer,which leads to the neglect of detailed information in some areas and the loss of local information,one-dimensional convolution is used instead of the shared fully-connected layer to achieve the task of weight calculation,so as to capture broader spatial information.In order to provide richer feature expression capabilities,a multi-head mechanism is introduced into the atten-tion mechanism to weight the importance of different parts of the features.In order to reduce the loss of information in the original image during feature extraction,ROI align is used to replace the ROI pooling algorithm.Finally,soft-NMS is introduced in the al-gorithm post-processing to replace the traditional NMS algorithm to reduce the missed and false detections.The experimental re-sults show that the improved faster R-CNN object detection network improves the localization ability of interested objects effec-tively,reduces the missed and false detections,and improves the average detection accuracy significantly.关键词
机器视觉/目标检测/Faster R-CNN/ROI Align/多头注意力机制/Soft-NMSKey words
machine vision/object detection/faster R-CNN/ROI align/multi-head attention mechanism/soft-NMS分类
电子信息工程引用本文复制引用
文靖杰,王勇,李金龙,张渝..多头自注意力机制的Faster R-CNN目标检测算法[J].现代电子技术,2024,47(7):8-16,9.基金项目
自然基金重点国际(地区)合作与交流项目(61960206010) （地区）
四川省科技计划项目(2021YJ0080) （2021YJ0080）
