发表机构
Zhejiang Lab; Beijing University of Posts and Telecommunications; Changsha University of Science and Technology; The Education University of Hong Kong; South China Agricultural University（之江实验室; 北京邮电大学; 长沙理工大学; 香港教育大学; 华南农业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对遥感变化检测，提出Freq-RemoteVAR框架，将其转为频域结构化生成问题，采用下一个频率预测范式，设计频率感知掩码令牌化等策略，经实验验证该方法在复杂场景中性能优于现有方法。
AI 中文摘要
遥感变化检测旨在从双时相图像中识别土地覆盖变化。大多数现有方法采用一次性密集预测范式，直接从融合特征回归变化掩码，但忽略了变化模式的内在频率特征。我们提出了Freq-RemoteVAR，一种频率自回归框架，将变化检测重新表述为频域中的结构化生成问题。引入下一个频率预测范式，通过傅里叶变换和量化将变化监督分解为多频率令牌目标，设计频率感知掩码令牌化策略。开发频率VAR Transformer对频率令牌进行因果自回归建模，引入Scale-Aligned RoPE Cross Attention (SRCA) 模块增强空间频率一致性，提出变化质量控制模块抑制伪变化响应并提高鲁棒性。在CDD、GZ-CD和LEVIR-CD上的大量实验表明，Freq-RemoteVAR始终优于现有方法，尤其是在具有复杂外观变化和噪声干扰的具有挑战性的场景中。
英文摘要
Remote sensing change detection aims to identify land-cover changes from bi-temporal images. Most existing methods follow a one-shot dense prediction paradigm, directly regressing a change mask from fused features. However, such approaches overlook the intrinsic frequency characteristics of change patterns. We propose Freq-RemoteVAR, a frequency autoregressive framework that reformulates change detection as a structured generation problem in the frequency domain. Instead of predicting the change mask in a single step, we introduce a next-frequency prediction paradigm, where change information is progressively generated from coarse to fine. We design a frequency-aware mask tokenization strategy that decomposes change supervision into multi-frequency token targets via Fourier transformation and quantization. We develop a Frequency VAR Transformer, which performs causal autoregressive modeling over frequency tokens. The model starts from learned mask queries and progressively predicts frequency-level tokens conditioned on previously generated tokens and bi-temporal image features, effectively capturing long-range dependencies across frequency scales. We introduce Scale-Aligned RoPE Cross Attention (SRCA) module, which aligns frequency-domain mask queries with spatial-domain bi-temporal features under a unified coordinate system, enhancing spatial-frequency consistency during generation. We propose a Change-quality Control module that adaptively modulates the generation process through dynamic normalization, attention biasing, and spatial offset adjustment, thereby suppressing pseudo-change responses and improving robustness. Extensive experiments on CDD, GZ-CD, and LEVIR-CD demonstrate that Freq-RemoteVAR consistently outperforms existing methods, particularly in challenging scenarios with complex appearance variations and noisy disturbances.
