仅上传嵌入向量，能高效实现遥感图像的机上检索与任务自适应。
Embedding-Only Uplink for Onboard Retrieval Under Shift in Remote Sensing
- 只上传紧凑嵌入和元数据，机上通过向量搜索筛选灾害图像。
- kNN检索在云分类中表现最优（0.92），而类别中心在变化检测中更优（0.85）。
- 同一嵌入可支持多任务适配，每查询传输量低于1KB，适合资源受限场景。
下行带宽限制促使机上系统优先处理风险图像而不传输原始像素。本文研究一种严苛设置：地面站仅上行紧凑嵌入与元数据，机上系统基于向量搜索对新采集图像进行分级。我们考察该嵌入仅上行流程在显式遥感数据分布偏移下的有效性，涵盖跨时间（灾前/灾后）、跨事件/地点（不同灾害）、跨站点云覆盖（15个地理站点）及跨城市区域（建筑）留出测试。基于OlmoEarth嵌入，在扩展的公开多任务基准（27景Sentinel-2 L2A影像、15个云站点、5个SpaceNet-2 AOI；10次随机种子）上，发现所有有效方法均依赖相同上行嵌入，但最优决策头任务相关：kNN检索在云分类中显著优于类别中心（0.92 vs. 0.91；p<0.01，Wilcoxon），而类别中心在时间变化检测中远胜于检索（0.85 vs. 0.48；p<0.01）。结果表明，嵌入仅上行是关键使能技术——一旦嵌入到达机上，系统即可按任务选择最优头，无需额外上行开销，所有遥测数据低于1KB/查询。
原文摘要 · Abstract (English)
Downlink bottlenecks motivate onboard systems that prioritize hazards without transmitting raw pixels. We study a strict setting where a ground station uplinks only compact embeddings plus metadata, and an onboard system performs vector search to triage new captures. We ask whether this embedding-only pipeline remains useful under explicit remote-sensing shift: cross-time (pre/post-event), cross-event/location (different disasters), cross-site cloud (15 geographic sites), and cross-city AOI holdout (buildings). Using OlmoEarth embeddings on a scaled public multi-task benchmark (27 Sentinel-2 L2A scenes, 15 cloud sites, 5 SpaceNet-2 AOIs; 10 seeds), we find that all effective methods rely on the same uplinked embeddings, but the optimal decision head is task-dependent: kNN retrieval is significantly superior for cloud classification (0.92 vs. centroid 0.91; p<0.01, Wilcoxon), while class centroids dominate temporal change detection (0.85 vs. retrieval 0.48; p<0.01). These results show that embedding-only uplink is the key enabler--once embeddings are onboard, the system can select the best head per task at no additional uplink cost, with all telemetry under 1 KB per query.
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。