Space target classification is regarded as a key technology for space situational awareness and security assurance. However, the generalization performance of conventional deep learning models remains limited under the small-sample regime due to scarce high-quality measured data, imbalanced class distribution, and environmental interference.To overcome this bottleneck, a hybrid method combining transfer learning (TL) and generative adversarial networks (GANs) was proposed. In this method, pretrained parameters and feature priors were transferred to the GAN to improve the quality of synthetic samples. The sample set expanded by the GAN was used to optimize the fine-tuning process of the transfer-learning model and enhance the adaptability to the target domain.The method was applied to the classification of small-sample space-target spectral data. The spectral data acquired by the 1.2 m photoelectric telescope at Changchun Station were processed by the proposed method. The similarities between the generated data and the original data are 81.97%, 82.06%, and 84.85% for the sample-based, feature-based, and sample-feature-fusion TL-GAN methods, respectively. The overall classification accuracies are 78.32%, 78.41%, and 81.05%, respectively. Compared to the case without generated data, the classification accuracies are increased by 2.25%, 2.28%, and 2.08% respectively.The proposed method improves feature-learning efficiency and classification accuracy. A new technical route for small-sample space target classification is provided by this method, offering both theoretical and practical support for the engineering application of space situational awareness systems.
YAO Jia-cheng, DENG Shi-yu, ZHANG Nan, KANG Zhe.
Application of Transfer Learning Generative Adversarial Network Combination Method to Target Classification in Small Sample Space Object[J].
Science Technology and Engineering, 2026, 26(23): 9770-9775 DOI:10.12404/j.issn.1671-1815.2508666
KesslerD J, Cour-PalaisB G. Collision frequency of artificial satellites: The creation of a debris belt[J]. Journal of Geophysical Research: Space Physics, 1978, 83(A6): 2637-2646.
[2]
LiZ, WangX, XuC, et al. Review of spectral characterization and identification of unresolved space objects[J]. Spectroscopy and Spectral Analysis, 2023, 43(5): 1329-1339.
[3]
VasileM, WalkerL, DunphyR D, et al. Intelligent characterisation of space objects with hyperspectral imaging[J]. Acta Astronautica, 2023, 203: 510-534.
[4]
VasileM, WalkerL, CampbellA, et al. Space object identification and classification from hyperspectral material analysis[J]. Scientific Reports, 2024, 14: 1570.
[5]
WangY, YaoQ, KwokJ T, et al. Generalizing from a few examples: a survey on few-shot learning[J]. ACM Computing Surveys, 2020, 53(3): 63.
[6]
BédardD, WadeG A. Time-resolved visible/near-infrared spectrometric observations of the Galaxy 11 geostationary satellite[J]. Advances in Space Research, 2017, 59(1): 212-229.
DingYigao, SunMingguo, LiZhenwei, et al. Observational data analysis of space objects with space debris photo-electric telescope array[J]. Science Technology and Engineering, 2019, 19(18): 25-31.
[9]
LiuS, ShiQ, ZhangL. Few-shot hyperspectral image classification with unknown classes using multitask deep learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(6): 5085-5102.
[10]
ZhangJ, LiuL, ZhaoR, et al. A Bayesian meta-learning-based method for few-shot hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5512215.
[11]
BrahamN A A, MouL, ChanussotJ, et al. Self-supervised learning for few-shot hyperspectral image classification[C]// IGARSS 2022—2022 IEEE International Geoscience and Remote Sensing Symposium. Kuala Lumpur: IEEE, 2022: 267-270.
[12]
ZhangD, RenY, LiuC, et al. Weighted contrastive prototype network for few-shot hyperspectral image classification with noisy labels[J]. Remote Sensing, 2024, 16(18): 3527.
QinJinchun, PeiHang, LiuBing, et al. Few-shot hyperspectral image classification with depth feature fusion[J]. Bulletin of Surveying and Mapping, 2025(11): 34-39.
DengShiyu, LiuChengzhi, KangZhe, et al. Automatic classification of massive stellar spectral data based on bias estimation convolutional neural network[J]. Science Technology and Engineering, 2021, 21(16): 6613-6618.
[19]
PanS J, YangQ. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2009, 22(10): 1345-1359.
[20]
MaY, ChenS, ErmonS, et al. Transfer learning in environmental remote sensing[J]. Remote Sensing of Environment, 2024, 301: 113924.
[21]
ZhengJ, WenY, ChenM, et al. Open-set domain adaptation for scene classification using multi-adversarial learning[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 208: 245-260.
[22]
QiuC, ZhangX, TongX, et al. Few-shot remote sensing image scene classification: Recent advances, new baselines, and future trends[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 209: 368-382.
[23]
ZhuJ, WenC, DuanC, et al. Radar moving target detection based on small-sample transfer learning and attention mechanism[J]. Remote Sensing, 2024, 16(22): 4325.
[24]
GoodfellowI, Pouget-AbadieJ, MirzaM, et al. Generative adversarial nets[C]// Advances in Neural Information Processing Systems 27 (NIPS 2014). Red Hook: Curran Associates, Inc., 2014: 2672-2680.
[25]
NashJ F. Equilibrium points in n-person games[J]. Proceedings of the National Academy of Sciences, 1950, 36(1): 48-49.