自动化学报2024，Vol.50Issue(7)：1305-1314,10.DOI:10.16383/j.aas.c210903
基于特征变换和度量网络的小样本学习算法
Feature Transformation and Metric Networks for Few-shot Learning
摘要
Abstract
For few-shot classification,training samples for each class are highly limited.Consequently,samples from the same class tend to distribute sparsely while boundaries between different classes are indistinct in the feature space.Therefore,a novel few-shot learning algorithm based on feature transformation and metric networks(FTMN)is proposed for few-shot learning.The algorithm maps samples to the feature space through an embedding function and calculates the residual between the input features and their class center.A feature transformation function is then constructed to learn from the residual,enabling input features to move closer to their class center after trans-formation.The transformed features are used to update the class centers,increasing the distance between centers of different classes.Furthermore,the algorithm introduces a novel metric function that jointly expresses the metric distances of each point within the features.The metric function simultaneously optimizes both cosine similarity and Euclidean distance.The performance of the algorithm on commonly used datasets for few-shot classification valid-ates its effectiveness and generalization ability.关键词
特征变换/度量学习/小样本学习/残差学习Key words
Feature transformation/metric learning/few-shot learning/residual learning引用本文复制引用
王多瑞,杜杨,董兰芳,胡卫明,李兵..基于特征变换和度量网络的小样本学习算法[J].自动化学报,2024,50(7):1305-1314,10.基金项目
国家重点研发计划(2018AAA0102802),国家自然科学基金(62036011,62192782,61721004),中国科学院前沿科学重点研究计划(QYZDJ-SSW-JSC040)资助Supported by National Key Research and Development Pro-gram of China(2018AAA0102802),National Natural Science Foundation of China(62036011,62192782,61721004),and Key Research Program of Frontier Sciences of Chinese Academy of Sciences(QYZDJ-SSW-JSC040) （2018AAA0102802）
