# Demystifying KAN for Vision Tasks: The RepKAN Approach

arXiv: https://arxiv.org/abs/2603.06002 · HTML: https://mlsanity.com/paper/2603.06002/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 13 of 13)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [KAN 2.0: Kolmogorov-Arnold Networks Meet Science](https://mlsanity.com/paper/2408.10205/) (2024)
- [RSMamba: Remote Sensing Image Classification with State Space Model](https://mlsanity.com/paper/2403.19654/) (2024)
- [Kolmogorov-Arnold Network for Satellite Image Classification in Remote Sensing](https://mlsanity.com/paper/2406.00600/) (2024)
- [Demonstrating the Efficacy of Kolmogorov-Arnold Networks in Vision Tasks](https://mlsanity.com/paper/2406.14916/) (2024)
- [MambaOutRS: A Hybrid CNN-Fourier Architecture for Remote Sensing Image Classification](https://mlsanity.com/paper/2506.19561/) (2025)
- [Bridging KAN and MLP: MJKAN, a Hybrid Architecture with Both Efficiency and Expressiveness](https://mlsanity.com/paper/2507.04690/) (2025)

## Abstract (arXiv)

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.