揭开KAN在视觉任务中的神秘面纱：RepKAN方法
Demystifying KAN for Vision Tasks: The RepKAN Approach
AI总结：
RepKAN通过结合CNN和KAN的优势，实现遥感图像分类的可解释性提升，优于现有模型。
摘要：
遥感图像分类对于地球观测至关重要，然而标准的CNN和Transformer通常充当不可解释的黑盒。我们提出了RepKAN，一种新的架构，它结合了CNN的结构效率与KAN的非线性表示能力。通过采用双路径设计——空间线性和频谱非线性——RepKAN能够自动发现类别特定的频谱指纹和物理交互流形。在EuroSAT和NWPU-RESISC45数据集上的实验结果表明，RepKAN提供了明确的物理可解释推理，并在性能上优于最先进的模型。这些发现表明，RepKAN有潜力成为未来可解释视觉基础模型的骨干。
英文摘要：
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.
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。
