AI RESEARCH
Demystifying KAN for Vision Tasks: The RepKAN Approach
arXiv CS.AI
•
ArXi:2603.06002v1 Announce Type: cross 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.