中北大学学报（自然科学版）2026，Vol.47Issue(3)：263-273,11.DOI:10.62756/jnuc.issn.1673-3193.2025.05.0003
基于改进Faster R-CNN的小样本目标检测算法
A Few-Shot Object Detection Algorithm Based on Improved Faster R-CNN
摘要
Abstract
In order to solve the problems of limited information that can be learned by the model due to the scarcity of training samples in few-shot scenarios,the performance of the model is restricted by the scale change of the object,and the catastrophic forgetting of the base class knowledge,a few-shot object detection algorithm with improved Faster R-CNN was proposed by following the transfer learning method.Firstly,in the feature extraction stage,the central coordinate attention mechanism was added to guide the model to learn the core features of the object,and multi-scale fusion and deformable convolution were introduced to enable the model to extract rich feature information on the feature map at different scales.Then,a gradual RPN was introduced,and a two-stage regression method was used to gradually optimize the generated regional suggestions.Finally,the knowledge compensation module was introduced to decouple the prior knowledge from the new knowledge with the help of the decoupling mechanism,so as to maintain a good memory of the base class.Experimental results show that,in the three novel class splits of the PASCAL VOC,compared with the mainstream small sample object detection method FSODCR,the proposed algorithm achieves an average increased in nAP by 8.37 percentage points and 6.63 percentage points in the 2-Shot and 5-Shot settings respectively;on the MS COCO,compared with FSODCR,the proposed algorithm achieves an average increase in nAP and nAP75 of 1.2 percentage points and 0.9 percentage points respectively under the 10-Shot,and nAP and nAP75 have increased by 1.2 percentage points and 0.8 percentage points under the 30-Shot,which significantly improves the accuracy and stability of object detection under few-shot conditions.关键词
目标检测/深度学习/小样本目标检测/迁移学习Key words
object detection/deep learning/few-shot object detection/transfer learning分类
信息技术与安全科学引用本文复制引用
李京,王子怡,巩海鑫,熊风光..基于改进Faster R-CNN的小样本目标检测算法[J].中北大学学报（自然科学版）,2026,47(3):263-273,11.基金项目
国家自然科学基金(62272426) （62272426）
山西省科技重大专项计划"揭榜挂帅"项目(202201150401021) （202201150401021）
山西省自然科学基金(202203021212138,202303021211153,202203021222027) （202203021212138,202303021211153,202203021222027）
山西省科技成果转化引导专项(202104021301055) （202104021301055）
