A Constrained Graph-Based Semi-Supervised Algorithm Combined with Particle Cooperation and Competition for Hyperspectral Image Classification

Abstract

Semi-supervised learning (SSL) focuses on the way to improve learning efficiency through the use of labeled and unlabeled samples concurrently. However, recent research indicates that the classification performance might be deteriorated by the unlabeled samples. Here, we proposed a novel graph-based semi-supervised algorithm combined with particle cooperation and competition, which can improve the model performance effectively by using unlabeled samples. First, for the purpose of reducing the generation of label noise, we used an efficient constrained graph construction approach to calculate the affinity matrix, which is capable of constructing a highly correlated similarity relationship between the graph and the samples. Then, we introduced a particle competition and cooperation mechanism into label propagation, which could detect and re-label misclassified samples dynamically, thus stopping the propagation of wrong labels and allowing the overall model to obtain better classification performance by using predicted labeled samples. Finally, we applied the proposed model into hyperspectral image classification. The experiments used three real hyperspectral datasets to verify and evaluate the performance of our proposal. From the obtained results on three public datasets, our proposal shows great hyperspectral image classification performance when compared to traditional graph-based SSL algorithms.

An outlook: machine learning in hyperspectral image classification and dimensionality reduction techniques

“…Therefore, SSL is gaining researchers' interest. 41 Self-training, 42 Active Learning (AL), 43 graphbased learning 44 and transductive learning 45 are some of the semi-supervised learning methodologies which are used to increase learning performance. The primary goal of all investigations is to increase the training sample size.…”