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 51 条
  • [1] Towards Open Set Deep Networks
    Bendale, Abhijit
    Boult, Terrance E.
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 1563 - 1572
  • [2] Bendale A, 2015, PROC CVPR IEEE, P1893, DOI 10.1109/CVPR.2015.7298799
  • [3] Adversarial Reciprocal Points Learning for Open Set Recognition
    Chen, Guangyao
    Peng, Peixi
    Wang, Xiangqian
    Tian, Yonghong
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (11) : 8065 - 8081
  • [4] Open Set Incremental Learning for Automatic Target Recognition
    Dang, Sihang
    Cao, Zongjie
    Cui, Zongyong
    Pi, Yiming
    Liu, Nengyuan
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (07): : 4445 - 4456
  • [5] Automatic Target Recognition in Synthetic Aperture Radar Imagery: A State-of-the-Art Review
    El-Darymli, Khalid
    Gill, Eric W.
    McGuire, Peter
    Power, Desmond
    Moloney, Cecilia
    [J]. IEEE ACCESS, 2016, 4 : 6014 - 6058
  • [6] Open-World Recognition in Remote Sensing: Concepts, challenges, and opportunities
    Fang, Leyuan
    Yang, Zhen
    Ma, Tianlei
    Yue, Jun
    Xie, Weiying
    Ghamisi, Pedram
    Li, Jun
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE, 2024, 12 (02) : 8 - 31
  • [7] SAR Target Incremental Recognition Based on Features With Strong Separability
    Gao, Fei
    Kong, Lingzhe
    Lang, Rongling
    Sun, Jinping
    Wang, Jun
    Hussain, Amir
    Zhou, Huiyu
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 13
  • [8] Ge ZY, 2017, Arxiv, DOI arXiv:1707.07418
  • [9] Recent Advances in Open Set Recognition: A Survey
    Geng, Chuanxing
    Huang, Sheng-Jun
    Chen, Songcan
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (10) : 3614 - 3631
  • [10] SAR Target Recognition via Random Sampling Combination in Open-World Environments
    Geng, Xiaojing
    Dong, Ganggang
    Xia, Ziheng
    Liu, Hongwei
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 (331-343) : 331 - 343