A novel semi-supervised learning method based on fast search and density peaks

Gao, Fei and Huang, Teng and Sun, Jinping and Hussain, Amir and Yang, Erfu and Zhou, Huiyu (2019) A novel semi-supervised learning method based on fast search and density peaks. Complexity, 2019. pp. 1-23. 6876173. ISSN 1076-2787 (https://doi.org/10.1155/2019/6876173)

[thumbnail of Gao-etal-Complexity2019-A-novel-semi-supervised-learning-method-based-on-fast-search] Text. Filename: Gao_etal_Complexity2019_A_novel_semi_supervised_learning_method_based_on_fast_search.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo

Download (9MB)


Radar image recognition is a hotspot in the field of remote sensing. Under the condition of sufficiently labeled samples, recognition algorithms can achieve good classification results. However, labeled samples are scarce and costly to obtain. Our major interest in this paper is how to use these unlabeled samples to improve the performance of a recognition algorithm in the case of limited labeled samples. This is a semi-supervised learning problem. However, unlike the existing semi-supervised learning methods, we do not use unlabeled samples directly and, instead, look for safe and reliable unlabeled samples before using them. In this paper, two new semi-supervised learning methods are proposed: a semi-supervised learning method based on fast search and density peaks (S 2 DP) and an iterative S 2 DP method (IS 2 DP). When the labeled samples satisfy a certain requirement, S2DP uses fast search and a density peak clustering method to detect reliable unlabeled samples based on the weighted kernel Fisher discriminant analysis (WKFDA). Then, a labeling method based on clustering information (LCI) is designed to label the unlabeled samples. When the labeled samples are insufficient, IS2DP is used to iteratively search for reliable unlabeled samples for semi-supervision. Then, these samples are added to the labeled samples to improve the recognition performance of S2DP. In the experiments, real radar images are used to verify the performance of our proposed algorithm in dealing with the scarcity of the labeled samples. In addition, our algorithm is compared against several semi-supervised deep learning methods with similar structures. Experimental results demonstrate that the proposed algorithm has better stability than these methods.