通过动态查询时空信息提升农田分割准确率
Think with Extra-Image: A Farmland Segmentation Agent Driven by Spatio-Temporal Information Gain
- 基于时空信息增益重构分割任务，主动获取额外上下文
- 在全局高分辨率数据集上实现更稳定的分割性能
- 适合需要高精度农田监测的遥感应用
现有农田遥感图像分割遵循“仅依赖单张图像”的范式，假设当前图像已包含足够视觉证据。然而，农田形态随物候和空间上下文变化，常与其它地表覆盖混淆，单一局部观测难以满足需求。因此，分割模糊性不仅源于模型表达能力不足，更根本在于所需时空信息超出当前图像范围。基于此，我们从信息瓶颈视角重新定义农田分割为由任务相关时空信息增益驱动的动态决策过程。提出FarmSeeker，一种动态分割智能体，可识别模糊区域、分析成因，并按需查询额外时空信息以实现精准分割。为评估该方法，构建了首个全球尺度、高分辨率的农田分割基准GSFS-Bench，支持推理-查询流程。实验表明，FarmSeeker在多种场景下表现优于现有方法。
原文摘要 · Abstract (English)
Existing farmland remote sensing image (FRSI) segmentation follows a "Think with Intra-Image" paradigm, assuming that the current image contains sufficient visual evidence for reliable segmentation. Yet farmland appearance varies with phenology and spatial context and is often confused with other land-cover, making instantaneous, local observations inadequate. Thus, segmentation ambiguity stems not only from limited model representation, but more fundamentally from the required spatio-temporal information lying beyond the current image. Based on this insight, we redefine FRSI segmentation from an information bottleneck perspective as a dynamic decision process driven by task-relevant extra spatio-temporal information gain. We further propose FarmSeeker, a dynamic FRSI segmentation agent that identifies ambiguous regions, reasons about their causes, and queries extra spatio-temporal information on demand for accurate segmentation. To evaluate FarmSeeker, we construct GSFS-Bench, the first global-scale, high-resolution FRSI segmentation benchmark that supports reasoning-querying. Experiments show that FarmSeeker achieves more stable segmentation performance than existing methods. The project is publicly available at: https://withoutocean.github.io/FarmSeeker/
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。