ViLaCD-R1: A Vision-Language Framework for Semantic Change Detection in Remote Sensing

TL;DR

ViLaCD-R1 is a two-stage vision-language framework that significantly improves semantic change detection accuracy and localization in remote sensing images by combining multimodal reasoning with mask-guided decoding.

Contribution

The paper introduces ViLaCD-R1, a novel two-stage framework that enhances semantic change detection through supervised fine-tuning and reinforcement learning, addressing localization and interpretability issues.

Findings

Achieves state-of-the-art accuracy on multiple benchmarks.

Robustly suppresses non-semantic variations.

Improves semantic change localization and boundary delineation.

Abstract

Remote sensing change detection (RSCD), a complex multi-image inference task, traditionally uses pixel-based operators or encoder-decoder networks that inadequately capture high-level semantics and are vulnerable to non-semantic perturbations. Although recent multimodal and vision-language model (VLM)-based approaches enhance semantic understanding of change regions by incorporating textual descriptions, they still suffer from challenges such as inaccurate spatial localization, imprecise pixel-level boundary delineation, and limited interpretability. To address these issues, we propose ViLaCD-R1, a two-stage framework comprising a Multi-Image Reasoner (MIR) and a Mask-Guided Decoder (MGD). Specifically, the VLM is trained through supervised fine-tuning (SFT) and reinforcement learning (RL) on block-level dual-temporal inference tasks, taking dual-temporal image patches as input and outputting a coarse change mask. Then, the decoder integrates dual-temporal image features with this coarse mask to predict a precise binary change map. Comprehensive evaluations on multiple RSCD benchmarks demonstrate that ViLaCD-R1 substantially improves true semantic change recognition and localization, robustly suppresses non-semantic variations, and achieves state-of-the-art accuracy in complex real-world scenarios.