IEEE Transactions on Aerospace and Electronic Systems · 2024 · 30 citations · 35 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDimensionality ReductionFeature DetectionImage ClassificationObject RecognitionOverfittingDecision CriterionSynthetic Aperture RadarTarget Recognition
As synthetic aperture radar (SAR) imaging technology continues to evolve, the growing repository of SAR images depicting diverse types of observed targets has sparked rising interest in SAR target incremental recognition techniques. However, most of the existing SAR target incremental recognition algorithms typically require an ample amount of training data. In urgent scenarios, such as emergency response and disaster relief, there may be a necessity to identify targets for which a substantial amount of data has not been previously accumulated. Algorithms designed for general scenarios often fail to achieve satisfactory performance in such situations. To tackle the aforementioned issues, this article presents a few-shot incremental recognition algorithm for SAR targets based on orthogonal distributed features. Specifically, an orthogonal distribution optimization method for features is designed, which not only mitigates the feature confusion in few-shot incremental learning, but also reserves space for features of potential unseen classes. A random augmentation method for high-dimensional features is proposed to improve the overfitting problem while assisting in strengthening the boundaries between features of different classes. Furthermore, a joint decision criterion based on the Euclidean distance and the cosine distance is introduced, enabling the classifier to possess sufficient generalization ability and robustness in handling dynamic data. Experimental results on the MSTAR dataset show that the algorithm outlined in this article outperforms existing methods in SAR target few-shot incremental recognition tasks, demonstrating its superior effectiveness.
35
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Few-Shot Class-Incremental Learning
Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang et al. · 2020 · 445 citations
Online continual learning in image classification: An empirical survey
Zheda Mai, Ruiwen Li, Jihwan Jeong et al. · Neurocomputing · 2021 · 381 citations
Few-Shot Incremental Learning with Continually Evolved Classifiers
Chi Zhang, Nan Song, Guosheng Lin et al. · 2021 · 341 citations