解决遥感图像多分支标签分类中层次信息利用不足的问题
MAPLE: Multi-Path Adaptive Propagation with Level-Aware Embeddings for Hierarchical Multi-Label Image Classification
- 通过层级感知嵌入与自适应传播，动态融合语义与视觉信息
- 在少样本场景下最高提升42%，参数增加仅2.6%
- 适合遥感图像中具有复杂层级结构的多标签分类任务
层次化多标签分类（HMLC）在遥感领域对建模结构化标签依赖关系至关重要。现有方法在多路径场景下表现不佳，因图像可能激活多个分类分支，导致层次信息利用不充分。本文提出MAPLE框架，整合三方面：(i) 基于图感知文本描述的层次语义初始化；(ii) 通过图卷积网络（GCNs）编码结构信息；(iii) 自适应多模态融合，动态平衡语义先验与视觉证据。设计自适应层级损失函数，自动为不同层级选择合适损失。在CORINE对齐的遥感数据集（AID、DFC-15、MLRSNet）上评估，少样本场景下性能最高提升42%，仅增加2.6%参数量，证明MAPLE能高效建模地球观测中的层次语义。
原文摘要 · Abstract (English)
Hierarchical multi-label classification (HMLC) is essential for modeling structured label dependencies in remote sensing. Yet existing approaches struggle in multi-path settings, where images may activate multiple taxonomic branches, leading to underuse of hierarchical information. We propose MAPLE (Multi-Path Adaptive Propagation with Level-Aware Embeddings), a framework that integrates (i) hierarchical semantic initialization from graph-aware textual descriptions, (ii) graph-based structure encoding via graph convolutional networks (GCNs), and (iii) adaptive multi-modal fusion that dynamically balances semantic priors and visual evidence. An adaptive level-aware objective automatically selects appropriate losses per hierarchy level. Evaluations on CORINE-aligned remote sensing datasets (AID, DFC-15, and MLRSNet) show consistent improvements of up to +42% in few-shot regimes while adding only 2.6% parameter overhead, demonstrating that MAPLE effectively and efficiently models hierarchical semantics for Earth observation (EO).
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。