SAR Target Incremental Recognition Based on Features With Strong Separability

计算机科学 人工智能 模式识别(心理学) 边界判定 卷积神经网络 遗忘 分类器(UML) 机器学习 聚类分析 渐进式学习 深度学习 人工神经网络 自动目标识别 合成孔径雷达 哲学 语言学
作者
Fei Gao,Lingzhe Kong,Rongling Lang,Jinping Sun,Jun Wang,Amir Hussain,Huiyu Zhou
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:62: 1-13 被引量:11
标识
DOI:10.1109/tgrs.2024.3351636
摘要

With the rapid development of deep learning technology, many synthetic aperture radar (SAR) target recognition algorithms based on convolutional neural networks have achieved exceptional performance on various datasets. However, conventional neural networks are repeatedly iterated on a fixed dataset until convergence, and once they learn new tasks, a large amount of previously learned knowledge is forgotten, leading to a significant decline in performance on old tasks. This article presents an incremental learning method based on strong separability features (SSF-IL) to address the model's forgetting of previously learned knowledge. The SSF-IL employs both intraclass and interclass scatter to compute the feature separability loss, in order to enhance the linear separability of features during incremental learning. In the process of learning new classes, an intraclass clustering loss is proposed to replace the conventional knowledge distillation. This loss function constrains the old class features to cluster around the saved class centers, maintaining the separability among the old class features. Finally, a classifier bias correction method based on boundary features is designed to reinforce the classifier's decision boundary and reduce classification errors. SAR target incremental recognition experiments are conducted on the MSTAR dataset, and the results are compared with several existing incremental learning algorithms to demonstrate the effectiveness of the proposed algorithm.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
斯文败类的应助被科研通管家采纳,获得10
刚刚
隐形曼青的应助被科研通管家采纳,获得10
刚刚
烟花的应助被科研通管家采纳,获得10
1秒前
今后的应助被科研通管家采纳,获得30
1秒前
Lucas的应助被科研通管家采纳,获得10
1秒前
wu完成签到 ,获得积分10
1秒前
1秒前
研友_VZG7GZ的应助被科研通管家采纳,获得10
1秒前
1秒前
1秒前
xxcub发布了新的文献求助10
1秒前
Ava的应助被科研通管家采纳,获得10
1秒前
1秒前
阿毛0226完成签到,获得积分10
2秒前
桐桐的应助被畅快的凡灵采纳,获得30
3秒前
qian发布了新的文献求助10
3秒前
4秒前
4秒前
科研通AI6.4的应助被luyiyi采纳,获得10
4秒前
4秒前
sufu_jony的应助被luyiyi采纳,获得10
4秒前
彭于晏的应助被2021采纳,获得10
5秒前
Djk520222发布了新的文献求助10
6秒前
sufu_jony的应助被不老实采纳,获得10
6秒前
xhj666完成签到,获得积分10
6秒前
wzbc完成签到,获得积分10
7秒前
科研通AI6.2的应助被王青奎采纳,获得10
7秒前
lllllllll发布了新的文献求助10
7秒前
7秒前
Tsuki发布了新的文献求助10
7秒前
llllhh发布了新的文献求助10
7秒前
7秒前
8秒前
小道发布了新的文献求助10
8秒前
里予完成签到 ,获得积分10
8秒前
null的应助被xxcub采纳,获得10
8秒前
9秒前
李健的应助被优美的冷雪采纳,获得10
9秒前
肥鸟先飞完成签到 ,获得积分10
9秒前
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8171477
求助须知:如何正确求助?哪些是违规求助? 9564248
关于积分的说明 21774106
捐赠科研通 7763073
什么是DOI,文献DOI怎么找? 3430972
关于科研通互助平台的介绍 2554805
邀请新用户注册赠送积分活动 2475887