AI RESEARCH

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

arXiv CS.CV

ArXi:2605.15582v1 Announce Type: new 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.