KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation
This work addresses agricultural monitoring needs by providing more efficient and explainable segmentation, though it is incremental as it builds on existing U-Net and KAN methods.
The paper tackled crop field segmentation by integrating Kolmogorov-Arnold networks (KANs) into U-Net architecture using Sentinel satellite images, achieving a 2% improvement in IoU with fewer GFLOPs compared to traditional U-Net.
Segmentation of crop fields is essential for enhancing agricultural productivity, monitoring crop health, and promoting sustainable practices. Deep learning models adopted for this task must ensure accurate and reliable predictions to avoid economic losses and environmental impact. The newly proposed Kolmogorov-Arnold networks (KANs) offer promising advancements in the performance of neural networks. This paper analyzes the integration of KAN layers into the U-Net architecture (U-KAN) to segment crop fields using Sentinel-2 and Sentinel-1 satellite images and provides an analysis of the performance and explainability of these networks. Our findings indicate a 2\% improvement in IoU compared to the traditional full-convolutional U-Net model in fewer GFLOPs. Furthermore, gradient-based explanation techniques show that U-KAN predictions are highly plausible and that the network has a very high ability to focus on the boundaries of cultivated areas rather than on the areas themselves. The per-channel relevance analysis also reveals that some channels are irrelevant to this task.