计算机科学与探索2024，Vol.18Issue(3)：693-706,14.DOI:10.3778/j.issn.1673-9418.2301070
双路径合作的原型矫正小样本分类模型
Prototype Rectification Few-Shot Classification Model with Dual-Path Cooperation
摘要
Abstract
In the learning process of the metric-based meta-learning,there are some problems,such as the lack of prior knowledge acquired due to the distribution of scarce data,the interference of weakly related or unrelated fea-tures extracted from a single-view sample,and the deviations of representative features caused by classification.To solve these problems,a prototype rectification few-shot classification model with dual-path cooperation is proposed in this paper.Firstly,the dual-path cooperation module adaptively highlights key features and weakens weakly related features from a multi-view perspective,and makes full use of feature information to obtain prior knowledge to im-prove the expression ability of features.Secondly,the problem of intra-class prototype with deviations is solved by the prototype rectification classification strategy with the sample feature information of the query set.Finally,the model parameters are updated reversely by means of the loss function,and the classification accuracy of the model is improved.Comparative experiments of 5-way 1-shot and 5-way 5-shot are conducted on five public datasets.Compared with baseline model,on the miniImageNet dataset,the accuracy is increased by 5.57 percentage points and 3.90 percentage points.On the tieredImageNet dataset,the accuracy is increased by 5.68 percentage points and 3.93 percentage points.On the CUB dataset,the accuracy is increased by 6.93 percentage points and 3.13 percent-age points.On the CIFAR-FS dataset,the accuracy is increased by 8.03 percentage points and 1.65 percentage points.On the FC-100 dataset,the accuracy is increased by 4.25 percentage points and 4.89 percentage points.Ex-perimental results show that the proposed model has good performance in the field of few-shot learning,and the modules in the model can be migrated to other models.关键词
小样本学习/元学习/度量学习/自适应双路径合作学习/原型矫正Key words
few-shot learning/meta-learning/metric learning/adaptive dual-path cooperation learning/prototype rectification分类
信息技术与安全科学引用本文复制引用
吕佳,曾梦瑶,董保森..双路径合作的原型矫正小样本分类模型[J].计算机科学与探索,2024,18(3):693-706,14.基金项目
国家自然科学基金重大项目(11991024) （11991024）
重庆市教委"成渝地区双城经济圈建设"科技创新项目(KJCX2020024) （KJCX2020024）
重庆市高校创新研究群体资助项目(CXQT20015) （CXQT20015）
重庆市教委科研项目重点项目(KJZD-K202200511).This work was supported by the Major Project of National Natural Science Foundation of China(11991024),the Science and Technology Innovation Project of"Chengdu-Chongqing Economic Circle Construction"of Chongqing Education Commission(KJCX2020024),the Innovative Research Group Foundation of Higher Education of Chongqing(CXQT20015),and the Key Research Project of Chongqing Education Commission(KJZD-K202200511). （KJZD-K202200511）
