Confidence-Guided Semi-supervised Learning in Land Cover Classification
This addresses the labor-intensive and expensive pixel-level labeling in large-scale land cover imagery, offering a domain-specific incremental improvement.
The paper tackles the problem of high labeling costs in land cover classification by developing a confidence-guided semi-supervised learning approach that uses high-confidence pseudo-labels and multiple network architectures, resulting in performance that surpasses classic semi-supervised methods and even fully supervised learning on the Potsdam dataset.
Semi-supervised learning has been well developed to help reduce the cost of manual labelling by exploiting a large quantity of unlabelled data. Especially in the application of land cover classification, pixel-level manual labelling in large-scale imagery is labour-intensive, time-consuming and expensive. However, existing semi-supervised learning methods pay limited attention to the quality of pseudo-labels during training even though the quality of training data is one of the critical factors determining network performance. In order to fill this gap, we develop a confidence-guided semi-supervised learning (CGSSL) approach to make use of high-confidence pseudo labels and reduce the negative effect of low-confidence ones for land cover classification. Meanwhile, the proposed semi-supervised learning approach uses multiple network architectures to increase the diversity of pseudo labels. The proposed semi-supervised learning approach significantly improves the performance of land cover classification compared to the classic semi-supervised learning methods and even outperforms fully supervised learning with a complete set of labelled imagery of the benchmark Potsdam land cover dataset.