提出高效融合光学与雷达影像的框架，提升云遮挡下的语义分割精度。
Lean Learning Beyond Clouds: Efficient Discrepancy-Conditioned Optical-SAR Fusion for Semantic Segmentation
- 用载体令牌三流编码器实现轻量级全局建模。
- 通过差异条件融合机制抑制云噪干扰，提升跨模态融合可靠性。
- 适合需要低延迟、高精度的遥感图像分割应用场景。
云遮挡严重破坏光学遥感图像的语义完整性。虽然合成孔径雷达（SAR）可提供互补观测，但在云干扰下实现高效的全局建模与可靠的跨模态融合仍具挑战。现有方法依赖密集全局注意力捕捉长程依赖，但会无差别传播云引起的噪声。提高鲁棒性通常需扩大模型容量，进一步增加计算开销。鉴于遥感应用的大规模与高分辨率特性，此类计算需求阻碍实际部署，造成效率与可靠性之间的权衡。为此，我们提出EDC框架，一种面向效率且基于差异条件的光学-SAR语义分割方法。三流编码器结合载体令牌，实现复杂度更低的紧凑全局上下文建模；引入差异条件混合融合（DCHF）机制，在全局聚合中选择性抑制不可靠区域以防止噪声污染；此外，设计辅助去云分支并采用教师指导的蒸馏，增强遮挡下的语义一致性。大量实验表明，EDC在M3M-CR和WHU-OPT-SAR数据集上分别提升mIoU 0.56%和0.88%，参数量减少46.7%，推理速度提升1.98倍。代码已开源：https://github.com/mengcx0209/EDC。
原文摘要 · Abstract (English)
Cloud occlusion severely degrades the semantic integrity of optical remote sensing imagery. While incorporating Synthetic Aperture Radar (SAR) provides complementary observations, achieving efficient global modeling and reliable cross-modal fusion under cloud interference remains challenging. Existing methods rely on dense global attention to capture long-range dependencies, yet such aggregation indiscriminately propagates cloud-induced noise. Improving robustness typically entails enlarging model capacity, which further increases computational overhead. Given the large-scale and high-resolution nature of remote sensing applications, such computational demands hinder practical deployment, leading to an efficiency-reliability trade-off. To address this dilemma, we propose EDC, an efficiency-oriented and discrepancy-conditioned optical-SAR semantic segmentation framework. A tri-stream encoder with Carrier Tokens enables compact global context modeling with reduced complexity. To prevent noise contamination, we introduce a Discrepancy-Conditioned Hybrid Fusion (DCHF) mechanism that selectively suppresses unreliable regions during global aggregation. In addition, an auxiliary cloud removal branch with teacher-guided distillation enhances semantic consistency under occlusion. Extensive experiments demonstrate that EDC achieves superior accuracy and efficiency, improving mIoU by 0.56\% and 0.88\% on M3M-CR and WHU-OPT-SAR, respectively, while reducing the number of parameters by 46.7\% and accelerating inference by 1.98$\times$. Our implementation is available at https://github.com/mengcx0209/EDC.
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。