IDN: inner-class dense neighbours for semi-supervised learning-based remote sensing scene classification

ABSTRACT

In remote sensing scene classification, manual annotation is time-consuming and expensive to collect, which limits the effective deployment of supervised classification networks. Semi-supervised learning (SSL), which can benefit from unlabelled and labelled samples simultaneously, attracts much attention. In this letter, we introduce a cluster group construction method for semi-supervised high-resolution remote sensing (HRRS) scene classification. The low-density separation assumption, which assumes that the decision boundary of a classification network should lie in the low-density region, is a vital assumption to guide the construction of clusters. Following this, we propose to construct inner-class dense neighbours (IDN) for the semi-supervised classification framework. The proposed IDN can increase the density of clusters for a better determination of high-density regions to help the network training in the SSL framework. The experiments on the NWPU-RESIS45 and RSSCN7 datasets demonstrate the effectiveness of our proposed method, which show that the performance of the classification network with our proposed IDN has a prominent classification accuracy improvement.

KEYWORDS:

• Semi-supervised learning
• scene classification
• remote sensing
• inner-class dense neighbours

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by the Natural Science Foundation of Jiangsu Province under Grant No. BK20220635, and in part by the National Natural Science Foundation of China under Grant No. 62201375 and 61671113.