LDGuid: A Framework for Robust Change Detection via Latent Difference Guidance

TL;DR

The paper introduces LDGuid, a framework that explicitly learns and injects semantic differences into change detection models, improving robustness and performance across multiple remote sensing datasets.

Contribution

It proposes a novel Latent Difference Guidance framework using adversarial autoencoding and information bottleneck to enhance change detection models.

Findings

LDGuid improves segmentation accuracy on multiple datasets.

It enhances robustness in noisy spectral conditions.

LDGuid effectively incorporates domain-specific knowledge.

Abstract

Modern deep learning models for change detection (CD) often struggle to explicitly represent task-relevant semantic differences. This paper proposes the Latent Difference Guidance (LDGuid) framework that explicitly learns and injects semantic differences into CD models. LDGuid deploys adversarial autoencoding to implement a difference embedding (DE) module. The DE module is pretrained via the information bottleneck method, restricting it to learn only task-relevant differences between pre- and post-event samples. The learned latent difference is then used as an explicit guidance signal in the CD model. We validate LDGuid by integrating it into U-Net, BIT, and AERNet baselines for CD and evaluating it on LEVIR-CD, WHU-CD, SVCD, and CaBuAr datasets. Experimental results show that LDGuid enhances segmentation performance across all benchmarks, with particularly remarkable gains in challenging settings affected by spectral noise. The results further highlight the ability of LDGuid in incorporating domain knowledge, such as task-specific spectral indices. Our findings suggest that semantic difference learning can drastically enhance the robustness of CD in remote sensing.