+高级检索
首页 > 过刊浏览>2025年第44卷第1期 >104-112. DOI:10.11972/j.issn.1001-9014.2025.01.014
PDF HTML阅读 XML下载 导出引用 引用提醒
基于交叉相关网络的少样本红外空中目标分类方法
作者:
作者单位:

1.中国科学院红外探测与成像技术重点实验室，上海 200083;2.中国科学院大学，北京 100049;3.中国科学院上海技术物理研究所，上海 200083

中图分类号:

TP391.4


Infrared aircraft few-shot classification method based on cross-correlation network
Author:
  • HUANG Zhen 1,2,3

    HUANG Zhen

    Key Laboratory of Infrared System Detection and Imaging Technology，Chinese Academy of Sciences，Shanghai 200083，China;University of Chinese Academy of Sciences，Beijing 100049，China;Shanghai Institute of Technical Physics，Chinese Academy of Sciences，Shanghai 200083，China
    在期刊界中查找
    在百度中查找
    在本站中查找
  • ZHANG Yong 1,3

    ZHANG Yong

    Key Laboratory of Infrared System Detection and Imaging Technology，Chinese Academy of Sciences，Shanghai 200083，China;Shanghai Institute of Technical Physics，Chinese Academy of Sciences，Shanghai 200083，China
    在期刊界中查找
    在百度中查找
    在本站中查找
  • GONG Jin-Fu 1,2,3

    GONG Jin-Fu

    Key Laboratory of Infrared System Detection and Imaging Technology，Chinese Academy of Sciences，Shanghai 200083，China;University of Chinese Academy of Sciences，Beijing 100049，China;Shanghai Institute of Technical Physics，Chinese Academy of Sciences，Shanghai 200083，China
    在期刊界中查找
    在百度中查找
    在本站中查找
Affiliation:

1.Key Laboratory of Infrared System Detection and Imaging Technology，Chinese Academy of Sciences，Shanghai 200083，China;2.University of Chinese Academy of Sciences，Beijing 100049，China;3.Shanghai Institute of Technical Physics，Chinese Academy of Sciences，Shanghai 200083，China

Fund Project:

Supported by the National Pre-research Program during the 14th Five-Year Plan（514010405）

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [35]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    针对红外空中目标样本匮乏、传统深度学习易产生过拟合等问题，提出一种基于交叉相关网络的少样本红外目标分类方法。该方法结合简单无参数自注意力和交叉注意力两个核心模块，通过分析支持图像和查询图像之间的自相关性和互相关性，实现少样本条件下红外目标的有效分类。所提出的交叉相关网络结合了这两个模块，以端到端的方式进行训练。其中，简单无参数自注意力负责提取图像内部结构，交叉注意力可以计算图像之间的互相关，进一步提取并融合图像之间的特征。与现有的小样本红外目标分类模型相比，该模型通过建模支持集和查询集之间特征的语义相关性，聚焦红外图像的几何结构和纹理信息，从而更好地关注目标对象。实验结果表明，该方法在各项分类任务中性能均优于现有的红外空中目标分类方法，且分类准确率最高提升超过3%。此外，消融实验和对比实验也证明了该方法的有效性。

    Abstract:

    In response to the scarcity of infrared aircraft samples and the tendency of traditional deep learning to overfit， a few-shot infrared aircraft classification method based on cross-correlation networks is proposed. This method combines two core modules： a simple parameter-free self-attention and cross-attention. By analyzing the self-correlation and cross-correlation between support images and query images， it achieves effective classification of infrared aircraft under few-shot conditions. The proposed cross-correlation network integrates these two modules and is trained in an end-to-end manner. The simple parameter-free self-attention is responsible for extracting the internal structure of the image while the cross-attention can calculate the cross-correlation between images further extracting and fusing the features between images. Compared with existing few-shot infrared target classification models， this model focuses on the geometric structure and thermal texture information of infrared images by modeling the semantic relevance between the features of the support set and query set， thus better attending to the target objects. Experimental results show that this method outperforms existing infrared aircraft classification methods in various classification tasks， with the highest classification accuracy improvement exceeding 3%. In addition， ablation experiments and comparative experiments also prove the effectiveness of the method.

    参考文献
    [1] Ning C， Liu W， Wang X. Infrared Object Recognition Based on Monogenic Features and Multiple Kernel Learning[C]// 2018 IEEE 3rd International Conference on Image， Vision and Computing （ICIVC） . 2018： 204-208. 10.1109/icivc.2018.8492872
    [2] Chen R M， Liu S J， Miao Z， et al. Infrared aircraft few-shot classification method based on meta learning[J]. Journal of Infrared and Millimeter Waves， 2021， 40（4）： 554-560.
    [3] Li W， Chen Q， Gu G， et al. Visible-infrared image matching based on parameter-free attention mechanism and target-aware graph attention mechanism[J]. Expert Systems with Applications， 2024， 238： 122038. 10.1016/j.eswa.2023.122038
    [4] Jin L， Liu S J， Wang X， et al. Infrared aircraft classification method with small samples based on improved relation network[J]. Acta Optica Sinica， 2020， 40（8）： 0811005. 10.3788/aos202040.0811005
    [5] Luo X， Wu H， Zhang J， et al. A closer look at few-shot classification again[C]// Proceedings of the 40th International Conference on Machine Learning . 2023， 202： 23103-23123.
    [6] Li X， Yang X， Ma Z， et al. Deep metric learning for few-shot image classification： A Review of recent developments[J]. Pattern Recognition， 2023， 138： 109381. 10.1016/j.patcog.2023.109381
    [7] Shi B， Li W， Huo J， et al. Global- and local-aware feature augmentation with semantic orthogonality for few-shot image classification[J]. Pattern Recognition， 2023， 142： 109702. 10.1016/j.patcog.2023.109702
    [8] Hou R， Chang H， Ma B， et al. Cross Attention Network for Few-shot Classification[C]// Advances in Neural Information Processing Systems . 2019， 32.
    [9] Kang D， Kwon H， Min J， et al. Relational Embedding for Few-Shot Classification[C]// 2021 IEEE/CVF International Conference on Computer Vision （ICCV） . 2021： 8802-8813. 10.1109/iccv48922.2021.00870
    [10] Li J. EACCNet： Enhanced Auto-Cross Correlation Network for Few-Shot Classification[C]// Knowledge Science， Engineering and Management . 2023， 14117： 354-365. 10.1007/978-3-031-40283-8_30
    [11] Kwon H， Kim M， Kwak S， et al. Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition[C]// 2021 IEEE/CVF International Conference on Computer Vision （ICCV） . 2021： 13045-13055. 10.1109/iccv48922.2021.01282
    [12] Lee S， Lee S， Seong H， et al. Revisiting Self-Similarity： Structural Embedding for Image Retrieval[C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2023： 23412-23421. 10.1109/cvpr52729.2023.02242
    [13] Wang L， Lei S， He J， et al. Self-Correlation and Cross-Correlation Learning for Few-Shot Remote Sensing Image Semantic Segmentation[C]// Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems . 2023： 1-10. 10.1145/3589132.3625570
    [14] Zhong Y， Su Y， Zhao H. Self-similarity feature based few-shot learning via hierarchical relation network[J]. International Journal of Machine Learning and Cybernetics， 2023， 14（12）： 4237-4249. 10.1007/s13042-023-01892-9
    [15] Yang L， Zhang R-Y， Li L， et al. SimAM： A Simple， Parameter-Free Attention Module for Convolutional Neural Networks[C]// Proceedings of the 38th International Conference on Machine Learning . 2021： 11863-11874. 10.1109/mlbdbi51377.2020.00079
    [16] Wen X， Cao C， Li Y， et al. DRSN with Simple Parameter-Free Attention Module for Specific Emitter Identification[C]// 2022 IEEE International Conference on Trust， Security and Privacy in Computing and Communications （TrustCom） . 2022： 192-200. 10.1109/trustcom56396.2022.00036
    [17] Tan S， Zhang L， Shu X， et al. A feature-wise attention module based on the difference with surrounding features for convolutional neural networks[J]. Frontiers of Computer Science， 2023， 17（6）： 176338. 10.1007/s11704-022-2126-1
    [18] Webb BS， Dhruv NT， Solomon SG， et al. Early and Late Mechanisms of Surround Suppression in Striate Cortex of Macaque[J]. Journal of Neuroscience， 2005， 25（50）： 11666-11675. 10.1523/jneurosci.3414-05.2005
    [19] Vinyals O， Blundell C， Lillicrap T， et al. Matching Networks for One Shot Learning[C]// Advances in Neural Information Processing Systems . 2016， 29.
    [20] Liu Q， Li X， Yuan D， et al. LSOTB-TIR： A Large-Scale High-Diversity Thermal Infrared Single Object Tracking Benchmark[J]. IEEE Transactions on Neural Networks and Learning Systems， 2023： 1-14. 10.1109/tnnls.2023.3236895
    [21] He K， Zhang X， Ren S， et al. Deep Residual Learning for Image Recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR） . 2016： 770-778. 10.1109/cvpr.2016.90
    [22] Ravi S， Larochelle H. Optimization as a model for few-shot learning[C]// International Conference on Learning Representations . 2017.
    [23] Finn C， Abbeel P， Levine S. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks[C]// Proceedings of the 34th International Conference on Machine Learning . 2017： 1126-1135. 10.1109/icra.2016.7487173
    [24] Hou R， Chang H， MA B， et al. Cross Attention Network for Few-shot Classification[C]// Advances in Neural Information Processing Systems . 2019， 32.
    [25] Li K， Zhang Y， Li K， et al. Adversarial Feature Hallucination Networks for Few-Shot Learning[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2020： 13467-13476. 10.1109/cvpr42600.2020.01348
    [26] Chen Z， Ge J， Zhan H， et al. Pareto Self-Supervised Training for Few-Shot Learning[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2021： 13658-13667. 10.1109/cvpr46437.2021.01345
    [27] Laenen S， Bertinetto L. On Episodes， Prototypical Networks， and Few-Shot Learning[C]// Advances in Neural Information Processing Systems . 2021， 34： 24581-24592.
    [28] Chen Y， Liu Z， Xu H， et al. Meta-Baseline： Exploring Simple Meta-Learning for Few-Shot Learning[C]//2021： 9062-9071. 10.1109/iccv48922.2021.00893
    [29] Qin Z， Wang H， Mawuli CB， et al. Multi-instance attention network for few-shot learning[J]. Information Sciences， 2022， 611： 464-475. 10.1016/j.ins.2022.07.013
    [30] Lazarou M， Stathaki T， Avrithis Y. Tensor feature hallucination for few-shot learning[C]// 2022 IEEE/CVF Winter Conference on Applications of Computer Vision （WACV） . 2022： 2050-2060. 10.1109/wacv51458.2022.00211
    [31] Hu J， Shen L， Sun G. Squeeze-and-Excitation Networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2018： 7132-7141. 10.1109/cvpr.2018.00745
    [32] Huang S， Wang Q， Zhang S， et al. Dynamic Context Correspondence Network for Semantic Alignment[C]//2019： 2010-2019. 10.1109/iccv.2019.00210
    [33] Ramachandran P， Parmar N， Vaswani A， et al. Stand-Alone Self-Attention in Vision Models[C]// Advances in Neural Information Processing Systems . 2019， 32.
    [34] Wang X， Girshick R， Gupta A， et al. Non-local Neural Networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . 2018： 7794-7803. 10.1109/cvpr.2018.00813
    [35] Woo S， Park J， Lee J-Y， et al. CBAM： Convolutional Block Attention Module[C]// Proceedings of the European conference on computer vision （ECCV） . 2018： 3-19. 10.1007/978-3-030-01234-2_1
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

黄臻,张湧,公劲夫.基于交叉相关网络的少样本红外空中目标分类方法[J].红外与毫米波学报,2025,44(1):104~112]. HUANG Zhen, ZHANG Yong, GONG Jin-Fu. Infrared aircraft few-shot classification method based on cross-correlation network[J]. J. Infrared Millim. Waves,2025,44(1):104~112.]

复制
分享
文章指标
  • 点击次数:24
  • 下载次数: 28
  • HTML阅读次数: 6
  • 引用次数: 0
历史
  • 收稿日期:2024-03-29
  • 最后修改日期:2024-11-10
  • 录用日期:2024-06-07
  • 在线发布日期: 2024-11-08
文章二维码
您是第12665983 位访问者
主管单位：中国科学院
主办单位：中国科学院上海技术物理研究所，中国光学学会
地址：上海市玉田路500号 电话：021-25051553
51La
红外与毫米波学报 ® 2025 版权所有