计算机工程与应用2024，Vol.60Issue(1)：254-262,9.DOI:10.3778/j.issn.1002-8331.2208-0245
融合分类校正与样本扩增的小样本目标检测
Few-Shot Object Detection Based on Fusion of Classification Correction and Sample Amplification
摘要
Abstract
Existing few-shot object detection methods often have the problem of data distribution shift when amplifying samples,and the performance of classification tasks is easily affected by localization tasks.Aiming at the above problems,a new few-shot object detection algorithm is proposed based on the Faster R-CNN framework.The classification correc-tion module(CCB),sample amplification module(SAB),and gradient control layer(GCL)are introduced to improve performance.CCB uses an offline strong classification network to correct the final results of the detector.SAB uses the base class information to modify the distribution of the new class samples in the feature domain,so as to complete the am-plification of the new class samples by sampling from the modified distribution.In gradient backpropagation,the informa-tion of the base class and new class received by the backbone network are restricted by GCL.The experimental results on PASCAL VOC and COCO datasets show that,compared with the latest known algorithm results,the proposed few-shot object detection algorithm improves the detection effect when the number of samples is small.The maximum improve-ment can reach 5.1%on PASCAL VOC,a public dataset.It also reaches up to 1.9%improvement on the more difficult dataset COCO.Therefore,the proposed few-shot detection framework has good robustness and generalization ability at the same time.关键词
小样本学习/目标检测/数据扩增/梯度限制Key words
few-shot learning/object detection/data amplification/gradient control分类
信息技术与安全科学引用本文复制引用
黄友文,豆恒,肖贵光..融合分类校正与样本扩增的小样本目标检测[J].计算机工程与应用,2024,60(1):254-262,9.基金项目
江西省教育厅科技项目(GJJ180443). （GJJ180443）
