Demystifying KAN for Vision Tasks: The RepKAN Approach
This addresses the need for interpretable models in Earth observation, offering a novel approach with potential for future visual foundation models, though it is incremental in combining existing methods.
The paper tackled the problem of uninterpretable black-box models in remote sensing image classification by proposing RepKAN, which integrates CNNs and KANs to enable interpretable reasoning, and it outperformed state-of-the-art models on EuroSAT and NWPU-RESISC45 datasets.
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.