Foundation Model-Driven Semantic Change Detection in Remote Sensing Imagery

TL;DR

This paper introduces a flexible, foundation model-based framework for semantic change detection in remote sensing imagery, achieving state-of-the-art results and high data efficiency.

Contribution

It proposes a modular cascaded decoder and a novel loss function to enhance semantic change detection across diverse models and conditions.

Findings

Achieves new state-of-the-art Sek scores on SECOND and LandsatSCD datasets.

Demonstrates high data efficiency, outperforming full-data baselines with only 50% data.

Shows robustness and generalization across different backbones and radiometric variations.

Abstract

Remote sensing (RS) change detection is essential for interpreting surface dynamics. Semantic change detection (SCD) further enables pixel-level understanding of multi-class transitions, yet remains sensitive to pseudo-changes induced by imaging conditions. Recent RS foundation models extract semantically consistent features across temporal and environmental variations, which is critical for mitigating pseudo-changes. However, existing SCD methods are often rigid and backbone-specific, lacking the flexibility to integrate diverse multi-scale features from emerging foundation models. To this end, we introduce a modular Cascaded Gated Decoder (CG-Decoder) that bridges various backbones and SCD tasks, processing multi-scale features in a coarse-to-fine manner while enabling adaptive change extraction. Building upon the RS foundation model PerA, we present PerASCD, a unified SCD framework. We further propose a Soft Semantic Consistency Loss (SSCLoss) to mitigate numerical instability in mixed-precision training. Extensive experiments on SECOND and LandsatSCD show that PerASCD achieves new state-of-the-art Sek scores (26.11% and 65.21%), surpassing the previous best by 0.61% and 4.95%, respectively. It also demonstrates exceptional data efficiency (outperforming the full-data baseline with 50% data), seamless cross-backbone generalization, and enhanced interpretability. Our approach maintains robust semantic consistency under radiometric variations, providing a reliable SCD solution. Code: https://github.com/SathShen/PerASCD.git.