C2F-SemiCD: A Coarse-to-Fine Semi-Supervised Change Detection Method Based on Consistency Regularization in High-Resolution Remote Sensing Images

TL;DR

This paper introduces a semi-supervised change detection method for high-resolution remote sensing images that uses a coarse-to-fine network with attention mechanisms and consistency regularization to improve accuracy while reducing labeling costs.

Contribution

The paper proposes a novel coarse-to-fine semi-supervised change detection framework with a multiscale attention network and a mean teacher update strategy, addressing label scarcity in remote sensing.

Findings

Significant improvement in change detection accuracy across three datasets.

Efficient semi-supervised learning reduces the need for extensive labeled data.

Ablation studies confirm the effectiveness of each component in the model.

Abstract

A high-precision feature extraction model is crucial for change detection (CD). In the past, many deep learning-based supervised CD methods learned to recognize change feature patterns from a large number of labelled bi-temporal images, whereas labelling bi-temporal remote sensing images is very expensive and often time-consuming; therefore, we propose a coarse-to-fine semi-supervised CD method based on consistency regularization (C2F-SemiCD), which includes a coarse-to-fine CD network with a multiscale attention mechanism (C2FNet) and a semi-supervised update method. Among them, the C2FNet network gradually completes the extraction of change features from coarse-grained to fine-grained through multiscale feature fusion, channel attention mechanism, spatial attention mechanism, global context module, feature refine module, initial aggregation module, and final aggregation module. The semi-supervised update method uses the mean teacher method. The parameters of the student model are updated to the parameters of the teacher Model by using the exponential moving average (EMA) method. Through extensive experiments on three datasets and meticulous ablation studies, including crossover experiments across datasets, we verify the significant effectiveness and efficiency of the proposed C2F-SemiCD method. The code will be open at: https://github.com/ChengxiHAN/C2F-SemiCDand-C2FNet.