首页 | 本学科首页   官方微博 | 高级检索  
     

基于深度网络的快速少样本学习算法
引用本文:代磊超,冯林,尚兴林,苏菡,龚勋.基于深度网络的快速少样本学习算法[J].模式识别与人工智能,2021,34(10):941-956.
作者姓名:代磊超  冯林  尚兴林  苏菡  龚勋
作者单位:四川师范大学 计算机科学学院 成都610101;西南交通大学 计算机与人工智能学院 成都611756
基金项目:国家自然科学基金项目(No.61876158)、中央高校基本科研业务费科技创新项目(No.2682021ZTPY030)资助
摘    要:少样本学习方法模拟人类从少量样本中学习的认知过程,已成为机器学习研究领域的热点.针对目前少样本学习迭代过程的任务量较大、过拟合现象严重等问题,文中提出基于深度网络的快速少样本学习算法.首先,利用核密度估计和图像滤波方法向训练集加入多种类型的随机噪声,生成支持集和查询集.再利用原型网络提取支持集和查询集图像特征,并根据Bregman散度,以每类支持集支持样本的中心点作为类原型.然后,使用L2范数度量支持集与查询图像的距离,利用交叉熵反馈损失,生成多个异构的基分类器.最后,采用投票机制融合基分类器的非线性分类结果.实验表明,文中算法能加快少样本学习收敛速度,分类准确率较高,鲁棒性较强.

关 键 词:深度网络  少样本学习  Bregman散度  度量学习
收稿时间:2021-07-26

Fast Few-Shot Learning Algorithm Based on Deep Network
DAI Leichao,FENG Lin,SHANG Xinglin,SU Han,GONG Xun.Fast Few-Shot Learning Algorithm Based on Deep Network[J].Pattern Recognition and Artificial Intelligence,2021,34(10):941-956.
Authors:DAI Leichao  FENG Lin  SHANG Xinglin  SU Han  GONG Xun
Affiliation:1. College of Computer Science, Sichuan Normal University, Chengdu 610101
2. School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756
Abstract:The cognitive process of the few-shot learning method simulating human learning from a small number of samples is one of the hotspots in the machine learning field. To solve the problems of large task volume and serious overfitting in the iterative process of the current few-shot learning methods, a fast few-shot learning algorithm based on deep network is proposed. Firstly, the kernel density estimation and image filtering methods are utilized to add multiple types of random noise to the training set to generate support sets and query sets. Then, the prototype network is applied to extract the image features of the support set and query set. According to the Bregman divergence, the center point of the support sample of each type of support set is employed as the class prototype. Then, the L2 norm is utilized to measure the distance between the support set and the query image. Multiple heterogeneous base classifiers are generated using cross-entropy feedback loss. Finally, the voting mechanism is introduced to fuse the nonlinear classification results of the base classifiers. Experiments show that the proposed algorithm speeds up the convergence of few-shot learning with higher classification accuracy and strong robustness.
Keywords:Deep Network  Few-Shot Learning  Bregman Divergence  Metric Learning  
本文献已被 万方数据 等数据库收录!
点击此处可从《模式识别与人工智能》浏览原始摘要信息
点击此处可从《模式识别与人工智能》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号