测量地球表示的内在维度
Measuring the Intrinsic Dimension of Earth Representations
AI总结:
本研究首次探讨地理隐式神经表示的内在维度,发现其内在维度在2-10之间,并与下游任务性能相关,可帮助评估和诊断模型。
摘要:
在地球观测的表示学习背景下,地理隐式神经表示(INRs)将低维位置输入(经度、纬度)嵌入到高维嵌入中,通过在地理参考的卫星、图像或文本数据上训练的模型实现。尽管地理INRs的共同目标是将地球的数据压缩成紧凑、易于学习的表示,但我们缺乏对这些地球表示中包含多少信息以及信息集中在哪里的理解。数据集的内在维度衡量的是捕捉其局部变化所需自由度的数量,无论其嵌入的高维空间。本研究首次探讨了地理INRs的内在维度。分析环境维度在256到512之间的INRs,我们发现其内在维度大致在2到10之间,并且对INR预训练期间的空间分辨率和输入模式的变化敏感。此外,我们还显示地理INR的内在维度与下游任务性能相关,并能捕捉空间伪影,从而促进模型评估和诊断。更广泛地说,我们的工作提供了一个架构无关、无标签的信息内容度量标准,可以跨INRs实现无监督评估、模型选择和预训练设计。
英文摘要:
Within the context of representation learning for Earth observation, geographic Implicit Neural Representations (INRs) embed low-dimensional location inputs (longitude, latitude) into high-dimensional embeddings, through models trained on geo-referenced satellite, image or text data. Despite the common aim of geographic INRs to distill Earth's data into compact, learning-friendly representations, we lack an understanding of how much information is contained in these Earth representations, and where that information is concentrated. The intrinsic dimension of a dataset measures the number of degrees of freedom required to capture its local variability, regardless of the ambient high-dimensional space in which it is embedded. This work provides the first study of the intrinsic dimensionality of geographic INRs. Analyzing INRs with ambient dimension between 256 and 512, we find that their intrinsic dimensions fall roughly between 2 and 10 and are sensitive to changing spatial resolution and input modalities during INR pre-training. Furthermore, we show that the intrinsic dimension of a geographic INR correlates with downstream task performance and can capture spatial artifacts, facilitating model evaluation and diagnostics. More broadly, our work offers an architecture-agnostic, label-free metric of information content that can enable unsupervised evaluation, model selection, and pre-training design across INRs.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。