Exploring Reinforced Class Separability and Discriminative Representations for SAR Target Open Set Recognition

被引:1
|
作者
Gao, Fei [1 ]
Luo, Xin [1 ]
Lang, Rongling [1 ]
Wang, Jun [1 ]
Sun, Jinping [1 ]
Hussain, Amir [2 ]
机构
[1] Beihang Univ, Sch Elect & Informat Engn, Beijing 100191, Peoples R China
[2] Edinburgh Napier Univ, Cyber & Big Data Res Lab, Edinburgh EH11 4BN, Scotland
基金
英国工程与自然科学研究理事会; 中国国家自然科学基金;
关键词
synthetic aperture radar (SAR); open set recognition (OSR); class separability reinforcement; discriminative feature capture; embedding space optimization; CLASSIFICATION;
D O I
10.3390/rs16173277
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Current synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms primarily operate under the closed-set assumption, implying that all target classes have been previously learned during the training phase. However, in open scenarios, they may encounter target classes absent from the training set, thereby necessitating an open set recognition (OSR) challenge for SAR-ATR. The crux of OSR lies in establishing distinct decision boundaries between known and unknown classes to mitigate confusion among different classes. To address this issue, we introduce a novel framework termed reinforced class separability for SAR target open set recognition (RCS-OSR), which focuses on optimizing prototype distribution and enhancing the discriminability of features. First, to capture discriminative features, a cross-modal causal features enhancement module (CMCFE) is proposed to strengthen the expression of causal regions. Subsequently, regularized intra-class compactness loss (RIC-Loss) and intra-class relationship aware consistency loss (IRC-Loss) are devised to optimize the embedding space. In conjunction with joint supervised training using cross-entropy loss, RCS-OSR can effectively reduce empirical classification risk and open space risk simultaneously. Moreover, a class-aware OSR classifier with adaptive thresholding is designed to leverage the differences between different classes. Consequently, our method can construct distinct decision boundaries between known and unknown classes to simultaneously classify known classes and identify unknown classes in open scenarios. Extensive experiments conducted on the MSTAR dataset demonstrate the effectiveness and superiority of our method in various OSR tasks.
引用
收藏
页数:25
相关论文
共 50 条
  • [31] Open Set Recognition and Category Discovery Framework for SAR Target Classification Based on K-Contrast Loss and Deep Clustering
    Chen, Mingyao
    Xia, Jing-Yuan
    Liu, Tianpeng
    Liu, Li
    Liu, Yongxiang
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 3489 - 3501
  • [32] Surrounding Prototype Loss for Radar HRRP Open Set Target Recognition
    Xia, Ziheng
    Wang, Penghui
    Dong, Ganggang
    Liu, Hongwei
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [33] Explainability of Deep Networks for SAR Target Recognition via Class Activation Mapping
    Cui Z.
    Yang Z.
    Jiang Y.
    Cao Z.
    Yang J.
    Journal of Radars, 2024, 13 (02) : 428 - 442
  • [34] Incremental Learning Based on Anchored Class Centers for SAR Automatic Target Recognition
    Li, Bin
    Cui, Zongyong
    Cao, Zongjie
    Yang, Jianyu
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [35] Class Hierarchy Aware Contrastive Feature Learning for Multigranularity SAR Target Recognition
    Wen, Zaidao
    Wang, Zikai
    Zhang, Jianting
    Lv, Yafei
    Wu, Qian
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2024, 60 (06) : 7962 - 7977
  • [36] Incremental Learning Based on Anchored Class Centers for SAR Automatic Target Recognition
    Li, Bin
    Cui, Zongyong
    Cao, Zongjie
    Yang, Jianyu
    IEEE Transactions on Geoscience and Remote Sensing, 2022, 60
  • [37] Compression based Class-Specific Target Recognition using SAR Images
    Kakoty, Jumi Hazarika
    Mishra, Amit Kumar
    2013 INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND EMBEDDED SYSTEMS (CARE-2013), 2013,
  • [38] Open-Set Recognition Using Intra-Class Splitting
    Schlachter, Patrick
    Liao, Yiwen
    Yang, Bin
    2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2019,
  • [39] Automatic threshold selection for multi-class open set recognition
    Scherreik, Matthew
    Rigling, Brian
    AUTOMATIC TARGET RECOGNITION XXVII, 2017, 10202
  • [40] Open Set Recognition through Unsupervised and Class-Distance Learning
    Draganov, Andrew
    Brown, Carter
    Mattei, Enrico
    Dalton, Cass
    Ranjit, Jaspreet
    PROCEEDINGS OF THE 2ND ACM WORKSHOP ON WIRELESS SECURITY AND MACHINE LEARNING, WISEML 2020, 2020, : 7 - 12