SpectralKAN: Weighted Activation Distribution Kolmogorov-Arnold Network for Hyperspectral Image Change Detection
This work addresses computational bottlenecks in applying KANs to high-dimensional hyperspectral image data, offering an incremental improvement for domain-specific change detection tasks.
The paper tackles the inefficiency of Kolmogorov-Arnold Networks (KANs) on high-dimensional data by proposing weighted activation distribution KANs (WKANs) and a multilevel tensor splitting framework (MTSF), resulting in SpectralKAN for hyperspectral image change detection that achieves an overall accuracy of 0.9801 and Kappa coefficient of 0.9514 on the Farmland dataset with only 8k parameters and 0.07 M FLOPs.
Kolmogorov-Arnold networks (KANs) represent data features by learning the activation functions and demonstrate superior accuracy with fewer parameters, FLOPs, GPU memory usage (Memory), shorter training time (TraT), and testing time (TesT) when handling low-dimensional data. However, when applied to high-dimensional data, which contains significant redundant information, the current activation mechanism of KANs leads to unnecessary computations, thereby reducing computational efficiency. KANs require reshaping high-dimensional data into a one-dimensional tensor as input, which inevitably results in the loss of dimensional information. To address these limitations, we propose weighted activation distribution KANs (WKANs), which reduce the frequency of activations per node and distribute node information into different output nodes through weights to avoid extracting redundant information. Furthermore, we introduce a multilevel tensor splitting framework (MTSF), which decomposes high-dimensional data to extract features from each dimension independently and leverages tensor-parallel computation to significantly improve the computational efficiency of WKANs on high-dimensional data. In this paper, we design SpectralKAN for hyperspectral image change detection using the proposed MTSF. SpectralKAN demonstrates outstanding performance across five datasets, achieving an overall accuracy (OA) of 0.9801 and a Kappa coefficient (K) of 0.9514 on the Farmland dataset, with only 8 k parameters, 0.07 M FLOPs, 911 MB Memory, 13.26 S TraT, and 2.52 S TesT, underscoring its superior accuracy-efficiency trade-off. The source code is publicly available at https://github.com/yanhengwang-heu/SpectralKAN.