双分支迭代的深度增量图像分类方法  

Deep Incremental Image Classification Method Based on Double-Branch Iteration

作　　者：何丽[1] 韩克平 朱泓西 刘颖 HE Li;HAN Keping;ZHU Hongxi;LIU Ying(School of Science and Technology,Tianjin University of Finance and Economics,Tianjin 300222)

机构地区：[1]天津财经大学理工学院,天津300222

出　　处：《模式识别与人工智能》2020年第2期150-159,共10页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.1170011574,61502331);天津市自然科学基金项目(No.16JCYBJC42000,18JCYBJC85100);天津市企业科技特派员项目(No.19JCTPJC56300);天津市教委科研项目(No.2017KJ237)资助。

摘　　要：针对深度增量学习可能产生灾难性遗忘的问题,提出双分支迭代的深度增量图像分类方法,使用主网络存储旧类知识,分支网络学习增量数据中的新类知识,并在增量过程中使用主网络的权重优化分支网络的参数.使用基于密度峰值聚类的方法从迭代数据集中筛选典型样本并构建保留集,并加入增量迭代训练中,减轻灾难性遗忘.实验表明,文中方法的性能较优.To solve the catastrophic forgetting problem caused by incremental learning,a deep incremental image classification method based on double-branch iteration is proposed.The primary network is utilized to store the acquired old class knowledge,while the branch network is exploited to learn the new class knowledge.The parameters of the branch network are optimized by the weight of the primary network in the incremental iteration process.Density peak clustering method is employed to select typical samples from the iterative dataset and construct retention set.The retention set is added into the incremental iteration training to mitigate catastrophic forgetting.The experiments demonstrate the better performance of the proposed method.

关 键 词：双分支卷积神经网络 保留集 增量学习 深度学习 图像分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]