类别数据流和特征空间双分离的类增量学习算法  

A Class Incremental Learning Algorithm with Dual Separation of Data Flow and Feature Space for Various Classes

作　　者：云涛 潘泉[1,3] 刘磊[4] 白向龙 刘宏 YUN Tao;PAN Quan;LIU Lei;BAI Xianglong;LIU Hong(School of Automation,Northwestern Polytechnical University,Xi’an 710114 China;State Key Laboratory of Astronautic Dynamics,Xi’an 710043,China;Key Laboratory of Information Fusion Technology of Ministry of Education,Xi’an 710114,China;Xidian University,Xi’an 710071,China)

机构地区：[1]西北工业大学自动化学院,西安710114 [2]宇航动力学国家重点实验室,西安710043 [3]信息融合技术教育部重点实验室,西安710114 [4]西安电子科技大学,西安710071

出　　处：《电子与信息学报》2024年第10期3879-3889,共11页Journal of Electronics & Information Technology

基　　金：国家自然科学基金重大项目(61790552)。

摘　　要：针对类增量学习(CIL)中的灾难性遗忘问题,该文提出一种不同类的数据流和特征空间双分离的类增量学习算法。双分离(S2)算法在1次增量任务中包含2个阶段。第1个阶段通过分类损失、蒸馏损失和对比损失的综合约束训练网络。根据模块功能对各类的数据流进行分离,以增强新网络对新类别的识别能力。通过对比损失的约束,增大各类数据在特征空间中的距离,避免由于旧类样本的不完备性造成特征空间被新类侵蚀。第2个阶段对不均衡的数据集进行动态均衡采样,利用得到的均衡数据集对新网络进行动态微调。利用实测和仿真数据构建了一个飞机目标高分辨率距离像增量学习数据集,实验结果表明该算法相比其它几种对比算法在保持高可塑性的同时,具有更高的稳定性,综合性能更优。To address the catastrophic forgetting problem in Class Incremental Learning(CIL),a class incremental learning algorithm with dual separation of data flow and feature space for various classes is proposed in this paper.The Dual Separation(S2)algorithm is composed of two stages in an incremental task.In the first stage,the network training is achieved through the comprehensive constraint of classification loss,distillation loss,and contrastive loss.The data flows from different classes are separated depending on module functions,in order to enhance the network’s ability to recognize new classes.By utilizing contrastive loss,the distance between different classes in the feature space is increased to prevent the feature space of old class from being eroded by the new class due to the incompleteness of the old class samples.In the second stage,the imbalanced dataset is subjected to dynamic balancing sampling to provide a balanced dataset for the new network’s dynamic fine-tuning.A high-resolution range profile incremental learning dataset of aircraft targets was created using observed and simulated data.The experimental results demonstrate that the algorithm proposed in this paper outperforms other algorithms in terms of overall performance and higher stability,while maintaining high plasticity.

关 键 词：雷达目标识别 逆合成孔径雷达 高分辨率距离像 类增量学习 

分 类 号：TN911.7[电子电信—通信与信息系统] TN959.17[电子电信—信息与通信工程]