MRIFE: A Mask-Recovering and Interactive-Feature-Enhancing Semantic Segmentation Network For Relic Landslide Detection

TL;DR

The paper introduces MRIFE, a novel semantic segmentation network that enhances relic landslide detection by improving feature extraction, addressing visual ambiguity, and effectively utilizing small datasets through contrastive learning and self-distillation.

Contribution

The paper proposes the MRIFE model with a contrastive learning and mask reconstruction approach, dual-branch feature enhancement, and self-distillation to improve relic landslide segmentation, especially on small datasets.

Findings

Significant improvement in precision from 0.4226 to 0.5347.

Increase in mean IoU from 0.6405 to 0.6680.

Enhanced landslide IoU from 0.3381 to 0.3934.

Abstract

Relic landslide, formed over a long period, possess the potential for reactivation, making them a hazardous geological phenomenon. While reliable relic landslide detection benefits the effective monitoring and prevention of landslide disaster, semantic segmentation using high-resolution remote sensing images for relic landslides faces many challenges, including the object visual blur problem, due to the changes of appearance caused by prolonged natural evolution and human activities, and the small-sized dataset problem, due to difficulty in recognizing and labelling the samples. To address these challenges, a semantic segmentation model, termed mask-recovering and interactive-feature-enhancing (MRIFE), is proposed for more efficient feature extraction and separation. Specifically, a contrastive learning and mask reconstruction method with locally significant feature enhancement is proposed to improve the ability to distinguish between the target and background and represent landslide semantic features. Meanwhile, a dual-branch interactive feature enhancement architecture is used to enrich the extracted features and address the issue of visual ambiguity. Self-distillation learning is introduced to leverage the feature diversity both within and between samples for contrastive learning, improving sample utilization, accelerating model convergence, and effectively addressing the problem of the small-sized dataset. The proposed MRIFE is evaluated on a real relic landslide dataset, and experimental results show that it greatly improves the performance of relic landslide detection. For the semantic segmentation task, compared to the baseline, the precision increases from 0.4226 to 0.5347, the mean intersection over union (IoU) increases from 0.6405 to 0.6680, the landslide IoU increases from 0.3381 to 0.3934, and the F1-score increases from 0.5054 to 0.5646.