Semi-LM: A Reliable Multiperspective Consistency Semi-Supervised Learning Framework for Landslide Mapping From Remote Sensing Images

Deep learning techniques have achieved significant success in landslide mapping (LM) from remote sensing images. However, the need for large quantities of high-quality labels presents a substantial barrier to the practical application of deep learning models. Semi-supervised learning (SSL) offers a solution by leveraging the knowledge contained in unlabeled remote sensing landslide images (RSLIs) to improve model performance. The main challenges in applying SSL to LM include the limitations and appropriateness of consistency perturbation perspectives, as well as the potential disruption of both shallow and deep landslide features and microtopographic information. To address these challenges, we propose a reliable multiperspective consistency SSL framework called Semi-LM. This framework employs multiperspective consistency learning (MCL) as the learning pathway and introduces the dual-branch anchor CutMix (DACM) method and feature perturbation assign (FPA) strategy for LM. MCL achieves unified multiperspective perturbations by enforcing the alignment of multiperspective perturbed LM results with generated weak perturbation pseudo-labels, expanding the perturbation space and enabling model to learn more discriminative features from unlabeled RSLIs. DACM generates anchor masks by determining NO-Cut zones with landslide anchors, mitigating the risk of erroneous knowledge accumulation and improving the reliability of model optimization. Additionally, by measuring the local variability of the model within a high-dimensional feature space, FPA identifies the specific stage where low-density regions of separated classes are located. Extensive comparative and ablation experiments on five diverse landslide datasets demonstrated that Semi-LM significantly reduces the reliance on labels in LM, identifies more landslides, and provides more stable results.