Enhanced SCanNet with CBAM and Dice Loss for Semantic Change Detection

TL;DR

This paper enhances semantic change detection in remote sensing images by integrating CBAM attention modules and Dice loss, leading to more accurate and robust land-cover change identification, especially under class imbalance and subtle boundary conditions.

Contribution

The study introduces a novel combination of CBAM attention modules and Dice loss into SCanNet, improving detection accuracy and robustness in semantic change detection tasks.

Findings

Improved detection accuracy on the SECOND dataset.

Clearer segmentation boundaries and better small-change region recovery.

Enhanced robustness against noisy inputs and class imbalance.

Abstract

Semantic Change Detection (SCD) in remote sensing imagery requires accurately identifying land-cover changes across multi-temporal image pairs. Despite substantial advancements, including the introduction of transformer-based architectures, current SCD models continue to struggle with challenges such as noisy inputs, subtle class boundaries, and significant class imbalance. In this study, we propose enhancing the Semantic Change Network (SCanNet) by integrating the Convolutional Block Attention Module (CBAM) and employing Dice loss during training. CBAM sequentially applies channel attention to highlight feature maps with the most meaningful content, followed by spatial attention to pinpoint critical regions within these maps. This sequential approach ensures precise suppression of irrelevant features and spatial noise, resulting in more accurate and robust detection performance compared to attention mechanisms that apply both processes simultaneously or independently. Dice loss, designed explicitly for handling class imbalance, further boosts sensitivity to minority change classes. Quantitative experiments conducted on the SECOND dataset demonstrate consistent improvements. Qualitative analysis confirms these improvements, showing clearer segmentation boundaries and more accurate recovery of small-change regions. These findings highlight the effectiveness of attention mechanisms and Dice loss in improving feature representation and addressing class imbalance in semantic change detection tasks.