RepKAN让遥感图像分类可解释，融合卷积与非线性优势。
Demystifying KAN for Vision Tasks: The RepKAN Approach
- 双路径设计：空间线性+光谱非线性，自动发现特征指纹。
- 在EuroSAT和NWPU-RESISC45上超越现有模型，精度提升显著。
- 适合需要可解释性的遥感、医学图像等高风险视觉任务。
遥感图像分类对地球观测至关重要，但标准CNN和Transformer常作为不可解释的黑箱。我们提出RepKAN，一种新架构，结合了CNN的结构效率与KAN的非线性表征能力。通过双路径设计——空间线性与光谱非线性——RepKAN能自主发现特定类别的光谱指纹和物理交互流形。在EuroSAT和NWPU-RESISC45数据集上的实验表明，RepKAN在提供明确物理可解释推理的同时，性能优于当前最先进模型。这些结果表明，RepKAN有潜力成为未来可解释视觉基础模型的核心架构。
原文摘要 · Abstract (English)
Remote sensing image classification is essential for Earth observation, yet standard CNNs and Transformers often function as uninterpretable black-boxes. We propose RepKAN, a novel architecture that integrates the structural efficiency of CNNs with the non-linear representational power of KANs. By utilizing a dual-path design -- Spatial Linear and Spectral Non-linear -- RepKAN enables the autonomous discovery of class-specific spectral fingerprints and physical interaction manifolds. Experimental results on the EuroSAT and NWPU-RESISC45 datasets demonstrate that RepKAN provides explicit physically interpretable reasoning while outperforming state-of-the-art models. These findings indicate that RepKAN holds significant potential to serve as the backbone for future interpretable visual foundation models.
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。