Task-Related Self-Supervised Learning for Remote Sensing Image Change Detection

TL;DR

This paper introduces TSLCD, a novel unsupervised change detection method for remote sensing images that enhances feature extraction, suppresses pseudo-changes, and improves accuracy through self-supervised learning and a smooth mechanism.

Contribution

The paper proposes a task-related self-supervised learning framework with a hard-sample-mining loss and smoothing mechanism, advancing remote sensing change detection accuracy.

Findings

Achieves state-of-the-art results on four datasets.

Effectively suppresses pseudo-changes and noise.

Improves feature representation for change detection.

Abstract

Change detection for remote sensing images is widely applied for urban change detection, disaster assessment and other fields. However, most of the existing CNN-based change detection methods still suffer from the problem of inadequate pseudo-changes suppression and insufficient feature representation. In this work, an unsupervised change detection method based on Task-related Self-supervised Learning Change Detection network with smooth mechanism(TSLCD) is proposed to eliminate it. The main contributions include: (1) the task-related self-supervised learning module is introduced to extract spatial features more effectively. (2) a hard-sample-mining loss function is applied to pay more attention to the hard-to-classify samples. (3) a smooth mechanism is utilized to remove some of pseudo-changes and noise. Experiments on four remote sensing change detection datasets reveal that the proposed TSLCD method achieves the state-of-the-art for change detection task.