计算机与现代化Issue(12)：7-13,23,8.DOI:10.3969/j.issn.1006-2475.2023.12.002
基于可学习记忆特征金字塔网络的小样本目标检测
Few-shot Object Detection via Learnable Memory Feature Pyramid Network
摘要
Abstract
At present,it is difficult to obtain the data of some industry application scenarios,and the problem of few shot has be-come an important factor restricting the application and promotion of deep learning technology.In this paper,few shot method is adopted to improve the performance of the model in the absence of data and reduce the dependence of the deep learning model on data,and few-shot object detection via learnable memory feature pyramid network is proposed to retain cleaner multi-scale fea-ture information for classifier prediction.With the help of the adaptive feature fusion module,the network can choose the empha-sis ratio among the features of different levels to maximize the retention of discriminant feature information of different scales.At the same time,we also add a retrospective feature alignment module to alleviate the feature confusion effect introduced by stack-ing feature layers.The experimental results show that the model performance can be effectively improved by overcoming the de-pendence on data,and the improved model can surpass other existing models of the same type in the COCO dataset and VOC da-taset.In particular,when the prior parameter k is set to 5 in VOC dataset,nAP50 increases by 4.8 to 44.7;when the prior param-eter k is set to 30 in COCO dataset,nAP50 increases by 4.0 to 29.4.关键词
小样本/自适应融合/特征对齐/特征金字塔网络Key words
few shot/adaptive fusion/feature alignment/feature pyramid network分类
信息技术与安全科学引用本文复制引用
夏千涵,何胜煌,吴元清,赵乐乐..基于可学习记忆特征金字塔网络的小样本目标检测[J].计算机与现代化,2023,(12):7-13,23,8.基金项目
国家自然科学基金资助项目(U22A2065,62003100,62276074) （U22A2065,62003100,62276074）
国家重点发展计划项目(2022YFB4701300) （2022YFB4701300）
广东省基础和应用基础研究基金资助项目(2021B15120058) （2021B15120058）
