用自回归模型提升遥感变化检测精度，克服传统方法的控制难与预测弱问题。
RemoteVAR: Autoregressive Visual Modeling for Remote Sensing Change Detection
- 通过跨注意力融合多分辨率双时相特征，增强模型对变化区域的感知能力。
- 在多个标准数据集上超越扩散模型和Transformer基线，显著提升变化检测准确率。
- 适合遥感图像分析、环境监测等需要高精度变化识别的应用场景。
遥感变化检测旨在定位并描述两个时间点之间的场景变化，广泛应用于环境监测与灾害评估。近年来，视觉自回归模型（VAR）在图像生成方面表现优异，但因其可控性差、密集预测性能不佳及暴露偏差，在像素级判别任务中应用受限。本文提出RemoteVAR，一种基于自回归框架的变化检测新方法，通过跨注意力机制将自回归预测条件化于多分辨率融合的双时相特征，并设计专用于变化图生成的自回归训练策略。在多个标准变化检测基准上的大量实验表明，RemoteVAR在各项指标上均显著优于强基线模型，包括扩散模型与Transformer模型，确立了自回归方法在遥感变化检测中的竞争力。代码将公开于https://github.com/yilmazkorkmaz1/RemoteVAR。
原文摘要 · Abstract (English)
Remote sensing change detection aims to localize and characterize scene changes between two time points and is central to applications such as environmental monitoring and disaster assessment. Meanwhile, visual autoregressive models (VARs) have recently shown impressive image generation capability, but their adoption for pixel-level discriminative tasks remains limited due to weak controllability, suboptimal dense prediction performance and exposure bias. We introduce RemoteVAR, a new VAR-based change detection framework that addresses these limitations by conditioning autoregressive prediction on multi-resolution fused bi-temporal features via cross-attention, and by employing an autoregressive training strategy designed specifically for change map prediction. Extensive experiments on standard change detection benchmarks show that RemoteVAR delivers consistent and significant improvements over strong diffusion-based and transformer-based baselines, establishing a competitive autoregressive alternative for remote sensing change detection. Code will be available \href{https://github.com/yilmazkorkmaz1/RemoteVAR}{\underline{here}}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。