Few-shot SAR target classification via meta-learning with hybrid models

被引:1
|
作者
Geng, Qingtian [1 ]
Wang, Yaning [1 ]
Li, Qingliang [1 ]
机构
[1] Changchun Normal Univ, Changchun, Jilin, Peoples R China
关键词
few-shot learning (FSL); adaptive dynamic weight hybrid model; synthetic aperture radar; automatic target recognition; meta-learning; NETWORK; ATR;
D O I
10.3389/feart.2024.1469032
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Currently, in Synthetic Aperture Radar Automatic Target Recognition (SAR ATR), few-shot methods can save cost and resources while enhancing adaptability. However, due to the limitations of SAR imaging environments and observation conditions, obtaining a large amount of high-value target data is challenging, leading to a severe shortage of datasets. This paper proposes the use of an Adaptive Dynamic Weight Hybrid Model (ADW-HM) meta-learning framework to address the problem of poor recognition accuracy for unknown classes caused by sample constraints. By dynamically weighting and learning model parameters independently, the framework dynamically integrates model results to improve recognition accuracy for unknown classes. Experiments conducted on the TASK-MSTAR and OpenSARShip datasets demonstrate that the ADW-HM framework can obtain more comprehensive and integrated feature representations, reduce overfitting, and enhance generalization capability for unknown classes. The accuracy is improved in both 1-shot and 5-shot scenarios, indicating that ADW-HM is feasible for addressing few-shot problems.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Few-shot classification via efficient meta-learning with hybrid optimization
    Jia, Jinfang
    Feng, Xiang
    Yu, Huiqun
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 127
  • [2] Meta-Learning Classification Network for Few-Shot Polarimetric SAR Images
    Luo, Huiqi
    Jiang, Nana
    Wang, Hui
    Guo, Jiao
    Zhu, Jubo
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2025, 22
  • [3] Fair Meta-Learning For Few-Shot Classification
    Zhao, Chen
    Li, Changbin
    Li, Jincheng
    Chen, Feng
    11TH IEEE INTERNATIONAL CONFERENCE ON KNOWLEDGE GRAPH (ICKG 2020), 2020, : 275 - 282
  • [4] Few-Shot Classification of Aerial Scene Images via Meta-Learning
    Zhang, Pei
    Bai, Yunpeng
    Wang, Dong
    Bai, Bendu
    Li, Ying
    REMOTE SENSING, 2021, 13 (01) : 1 - 21
  • [5] Few-Shot One-Class Classification via Meta-Learning
    Frikha, Ahmed
    Krompass, Denis
    Koepken, Hans-Georg
    Tresp, Volker
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 7448 - 7456
  • [6] Few-Shot Directed Meta-Learning for Image Classification
    Ouyang, Jihong
    Duan, Ganghai
    Liu, Siguang
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2023, 37 (01)
  • [7] Unsupervised Meta-Learning for Few-Shot Image Classification
    Khodadadeh, Siavash
    Boloni, Ladislau
    Shah, Mubarak
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [8] Contrastive Meta-Learning for Few-shot Node Classification
    Wang, Song
    Tan, Zhen
    Liu, Huan
    Li, Jundong
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 2386 - 2397
  • [9] Few-shot Edge Classification in Graph Meta-learning
    Yang, Xiaoxiao
    Xu, Jungang
    2022 IEEE 9TH INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA), 2022, : 166 - 172
  • [10] Meta-Learning for Few-Shot Land Cover Classification
    Russwurm, Marc
    Wang, Sherrie
    Koerner, Marco
    Lobell, David
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, : 788 - 796