# Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition

arXiv: https://arxiv.org/abs/2604.01903 · HTML: https://mlsanity.com/paper/2604.01903/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 72 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2311.15153/) (2023)
- [Unveiling the Power of Wavelets: A Wavelet-based Kolmogorov-Arnold Network for Hyperspectral Image Classification](https://mlsanity.com/paper/2406.07869/) (2024)
- [Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studies](https://mlsanity.com/paper/2407.01092/) (2024)
- [SARATR-X: Toward Building A Foundation Model for SAR Target Recognition](https://mlsanity.com/paper/2405.09365/) (2024)
- [Lightweight Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2402.00422/) (2024)
- [A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution](https://mlsanity.com/paper/2404.15620/) (2024)
- [A Causal Adjustment Module for Debiasing Scene Graph Generation](https://mlsanity.com/paper/2503.17862/) (2025)
- [MaDiNet: Mamba Diffusion Network for SAR Target Detection](https://mlsanity.com/paper/2411.07500/) (2024)
- [ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild](https://mlsanity.com/paper/2501.13354/) (2025)
- [ASANet: Asymmetric Semantic Aligning Network for RGB and SAR image land cover classification](https://mlsanity.com/paper/2412.02044/) (2024)
- [Rapid Salient Object Detection with Difference Convolutional Neural Networks](https://mlsanity.com/paper/2507.01182/) (2025)
- [KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation](https://mlsanity.com/paper/2408.07040/) (2024)
- [Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulation](https://mlsanity.com/paper/2406.08896/) (2024)
- [Fifty Years of SAR Automatic Target Recognition: The Road Forward](https://mlsanity.com/paper/2509.22159/) (2025)
- [SpectralKAN: Weighted Activation Distribution Kolmogorov-Arnold Network for Hyperspectral Image Change Detection](https://mlsanity.com/paper/2407.00949/) (2024)
- [S4ST: A Strong, Self-transferable, faSt, and Simple Scale Transformation for Transferable Targeted Attack](https://mlsanity.com/paper/2410.13891/) (2024)

## Built on by (most cited first, 1 of 1)

- [Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs](https://mlsanity.com/paper/2606.24371/) (2026)

## Abstract (arXiv)

Synthetic Aperture Radar (SAR) image recognition is vital for disaster monitoring, military reconnaissance, and ocean observation. However, large SAR image sizes hinder deep learning deployment on resource-constrained edge devices, and existing lightweight models struggle to balance high-precision feature extraction with low computational requirements. The emerging Kolmogorov-Arnold Network (KAN) enhances fitting by replacing fixed activations with learnable ones, reducing parameters and computation. Inspired by KAN, we propose Light-ResKAN to achieve a better balance between precision and efficiency. First, Light-ResKAN modifies ResNet by replacing convolutions with KAN convolutions, enabling adaptive feature extraction for SAR images. Second, we use Gram Polynomials as activations, which are well-suited for SAR data to capture complex non-linear relationships. Third, we employ a parameter-sharing strategy: each kernel shares parameters per channel, preserving unique features while reducing parameters and FLOPs. Our model achieves 99.09%, 93.01%, and 97.26% accuracy on MSTAR, FUSAR-Ship, and SAR-ACD datasets, respectively. Experiments on MSTAR resized to 1024 × 1024 show that compared to VGG16, our model reduces FLOPs by 82.90 × and parameters by 163.78 ×. This work establishes an efficient solution for edge SAR image recognition.