CEBSNet: Change-Excited and Background-Suppressed Network with Temporal Dependency Modeling for Bitemporal Change Detection

TL;DR

CEBSNet is a novel neural network that models temporal dependencies and suppresses background noise to improve pixel-level change detection in diverse and challenging remote sensing and street view images.

Contribution

It introduces a new network architecture with modules for temporal dependency modeling and change region enhancement, addressing limitations of previous methods.

Findings

Achieves state-of-the-art performance on multiple datasets.

Effectively detects both obvious and subtle changes.

Improves robustness against illumination and seasonal variations.

Abstract

Change detection, a critical task in remote sensing and computer vision, aims to identify pixel-level differences between image pairs captured at the same geographic area but different times. It faces numerous challenges such as illumination variation, seasonal changes, background interference, and shooting angles, especially with a large time gap between images. While current methods have advanced, they often overlook temporal dependencies and overemphasize prominent changes while ignoring subtle but equally important changes. To address these limitations, we introduce \textbf{CEBSNet}, a novel change-excited and background-suppressed network with temporal dependency modeling for change detection. During the feature extraction, we utilize a simple Channel Swap Module (CSM) to model temporal dependency, reducing differences and noise. The Feature Excitation and Suppression Module (FESM) is developed to capture both obvious and subtle changes, maintaining the integrity of change regions. Additionally, we design a Pyramid-Aware Spatial-Channel Attention module (PASCA) to enhance the ability to detect change regions at different sizes and focus on critical regions. We conduct extensive experiments on three common street view datasets and two remote sensing datasets, and our method achieves the state-of-the-art performance.