用检索增强方法提升地理嵌入的视觉信息保留，显著改善地理分类与回归任务性能。
RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings
- 通过检索相似位置图像融合视觉特征，增强地理嵌入表征能力。
- 在分类任务上最高提升13.1%，回归任务提升0.145 $R^2$。
- 适合需要高精度地理表征的遥感、生态分类等下游任务使用。
地理位置的表示选择对多种地理空间任务的准确性有重要影响，包括细粒度物种分类、人口密度估计和生物群落分类。现有方法如SatCLIP和GeoCLIP通过对比对齐地理位置与共位图像来学习表示。尽管效果优异，本文指出当前训练策略未能充分捕捉关键视觉特征，并从信息论角度说明此类方法会丢失对下游任务至关重要的视觉信息。为此，我们提出一种新的检索增强策略RANGE。该方法基于直观假设：一个位置的视觉特征可通过组合多个外观相似位置的视觉特征来估计。我们在多种任务上评估该方法，结果表明，RANGE在多数任务中显著优于现有最先进模型，在分类任务上最高提升13.1%，在回归任务上提升0.145 $R^2$。所有代码与模型将公开于https://github.com/mvrl/RANGE。
原文摘要 · Abstract (English)
The choice of representation for geographic location significantly impacts the accuracy of models for a broad range of geospatial tasks, including fine-grained species classification, population density estimation, and biome classification. Recent works like SatCLIP and GeoCLIP learn such representations by contrastively aligning geolocation with co-located images. While these methods work exceptionally well, in this paper, we posit that the current training strategies fail to fully capture the important visual features. We provide an information-theoretic perspective on why the resulting embeddings from these methods discard crucial visual information that is important for many downstream tasks. To solve this problem, we propose a novel retrieval-augmented strategy called RANGE. We build our method on the intuition that the visual features of a location can be estimated by combining the visual features from multiple similar-looking locations. We evaluate our method across a wide variety of tasks. Our results show that RANGE outperforms the existing state-of-the-art models with significant margins in most tasks. We show gains of up to 13.1% on classification tasks and 0.145 $R^2$ on regression tasks. All our code and models will be made available at: https://github.com/mvrl/RANGE.
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。