基于对称卷积块网络和原型校准的小样本学习方法  

Few-Shot Learning Method Based on Symmetric Convolutional Block Network and Prototype Calibration

作　　者：刘帅 白雪飞[1] 高小方[1] LIU Shuai;BAI Xuefei;GAO Xiaofang(School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China)

机构地区：[1]山西大学计算机与信息技术学院,太原030006

出　　处：《计算机科学》2024年第11期182-190,共9页Computer Science

基　　金：国家自然科学基金(61703252,62276161);山西省重点研发项目(202102150401013);山西省回国留学人员科研资助项目(2022-008)。

摘　　要：针对基于原型网络的小样本学习模型泛化能力不足以及由少量样本得到的类原型不准确等问题,提出一种新的小样本学习方法。首先采用一个由双向卷积块注意力模块和残差块构成的对称网络SCB-Net对图像不同深度的特征进行自适应学习,从而提取到更具代表性的类别特征表示,以有效提高模型的泛化能力;其次提出了一种反欧氏标签传播原型校准算法IELP-PC,利用伪标签策略扩充支持集样本;最后在支持集样本上采用反欧氏距离加权对类原型进行校准,进而提高模型的分类精度。在两个常用数据集mini-ImageNet和tiered-ImageNet上进行了实验,结果验证了所提方法的有效性,与基线模型相比,其在5-way 1-shot上分别提高了6.44%和7.83%,在5-way 5-shot上分别提高了2.68%和2.02%。To address the issues of poor generalization performance in few-shot learning models based on prototype networks and inaccurate class prototypes obtained from a small number of samples,a novel few-shot learning method is proposed in this paper.Firstly,a symmetric convolutional block network(SCB-Net)consisting of bidirectional convolutional block attention modules and residual blocks is used to adaptively learn the features at different depths of the image,so as to extract a more representative representation of the category features and effectively improve the generalization ability of the model.Secondly,an inverse Euclidean label propagation prototype calibration algorithm(IELP-PC)is introduced.It employs pseudo-labeling to augment the support set samples and subsequently calibrates the class prototypes using inverse Euclidean distance weighting for the support set samples,thereby improving the model's classification accuracy.Experiment results on two commonly used datasets mini-ImageNet and tiered-ImageNet demonstrate the effectiveness of the proposed method.Compared with the baseline model,the proposed method improves the 5-way 1-shot accuracy by 6.44%and 7.83%,and the 5-way 5-shot accuracy by 2.68%and 2.02%,respectively.

关 键 词：原型网络 小样本学习 对称卷积块网络 原型校准 反欧氏距离 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]