电子科技2024，Vol.37Issue(8)：75-83,9.DOI:10.16180/j.cnki.issn1007-7820.2024.08.011
基于非局部支持注意力的小样本目标检测算法
Non-Local Support Attention Network for Few-Shot Object Detection
摘要
Abstract
The key point of current research on few-shot object detection based on meta-learning is how to make better use of the information of support branch to help query branch to recognize novel objects more effectively.However,many current methods fuse the features from support branch and query branch in the depth direction,igno-ring the spatial position relationship between features.Therefore,this study proposes non-local support attention network.This method not only adds support information into the proposals features,but also fuses the support infor-mation with the features that fed into region proposal network.The spatial position relationship between features is considered at the same time.It also adds the information of negative supports to the detection module to help the mod-el distinguish the objects from different categories.This method obtains good performance on base classes and novel classes of COCO2017 dataset,particularly under the case of incremental learning.Compared with method before im-provement,3.3/3.8/4.7 mAP is increased in AP/AP50/AP75 of novel classes.2.7/0.5/3.3 mAP is increased in AP/AP50/AP75 of the base classes,and outperformed the performance of SOTA(Sort-Of-The-Art)model DAnA(Dual-Awareness Attention)under the same setting.关键词
目标检测/小样本学习/元学习/增量式学习/特征融合/注意力/非局部/微调Key words
object detection/few-shot learning/meta-learning/incremental learning/feature fusion/attention/non-local/fine-tuning分类
信息技术与安全科学引用本文复制引用
谢熙君,李菲菲..基于非局部支持注意力的小样本目标检测算法[J].电子科技,2024,37(8):75-83,9.基金项目
上海市高校特聘教授(东方学者)岗位计划(ES2015XX)Program for Professor of Special Appointment(Eastern Scholar)at Shanghai Institutions of Higher Learning(ES2015XX) （东方学者）
