用特征级对比学习提升遥感表格数据的表征能力
ZAYAN: Disentangled Contrastive Transformer for Tabular Remote Sensing Data
- 在特征层面做对比学习，无需锚点或标签
- 在8个数据集上超越现有方法，尤其在少样本时表现更好
- 适合遥感、环境科学中的表格数据建模
遥感与环境科学中的表格数据因异质性、标签稀缺和特征冗余，学习有效表征极具挑战。我们提出ZAYAN（Zero-Anchor dYnamic feAture eNcoding），一种自监督、以特征为中心的对比学习框架。ZAYAN在特征层面而非样本层面进行对比学习，无需显式锚点选择或依赖类别标签，同时促使嵌入空间冗余最小化、解耦。该框架包含两个模块：ZAYAN-CL通过零锚点对比目标结合动态扰动与掩码预训练特征嵌入；ZAYAN-T为基于这些嵌入的Transformer，用于下游分类。在八个数据集上验证，包括六个遥感表格基准及两个基于卫星与GIS产品的洪水预测表格，ZAYAN在准确率、鲁棒性和泛化能力上均优于现有深度学习基线，且在标签稀缺和分布偏移条件下持续取得优势。结果表明，特征级对比学习与动态特征编码是学习遥感表格数据的有效方案。
原文摘要 · Abstract (English)
Learning informative representations from tabular data in remote sensing and environmental science is challenging due to heterogeneity, scarce labels, and redundancy among features. We present ZAYAN (Zero-Anchor dYnamic feAture eNcoding), a self-supervised, feature-centric contrastive framework for tabular data. ZAYAN performs contrastive learning at the feature rather than sample level, removing the need for explicit anchor selection and any reliance on class labels, while encouraging a redundancy-minimized, disentangled embedding space. The framework has two modules: ZAYAN-CL, which pretrains feature embeddings via a zero-anchor contrastive objective with dynamic perturbations and masking, and ZAYAN-T, a Transformer that conditions on these embeddings for downstream classification. Across eight datasets, including six remote-sensing tabular benchmarks and two remote-sensing-driven flood-prediction tables from satellite and GIS products, ZAYAN achieves superior accuracy, robustness, and generalization over tabular deep learning baselines, with consistent gains under label scarcity and distribution shift. These results indicate that feature-level contrastive learning and dynamic feature encoding provide an effective recipe for learning from tabular sensing data.
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。