Suitability of KANs for Computer Vision: A preliminary investigation

TL;DR

This paper evaluates the potential of Kolmogorov-Arnold Networks (KANs) in computer vision tasks, comparing their performance and efficiency with traditional models, and discusses their strengths and limitations.

Contribution

It provides a preliminary assessment of KANs' applicability to visual recognition and segmentation, highlighting the importance of complex edge functions for performance.

Findings

KAN-based architectures perform comparably to traditional models

Complex functions on network edges improve performance on complex visual data

KANs show promise but require further research for optimal application

Abstract

Kolmogorov-Arnold Networks (KANs) introduce a paradigm of neural modeling that implements learnable functions on the edges of the networks, diverging from the traditional node-centric activations in neural networks. This work assesses the applicability and efficacy of KANs in visual modeling, focusing on fundamental recognition and segmentation tasks. We mainly analyze the performance and efficiency of different network architectures built using KAN concepts along with conventional building blocks of convolutional and linear layers, enabling a comparative analysis with the conventional models. Our findings are aimed at contributing to understanding the potential of KANs in computer vision, highlighting both their strengths and areas for further research. Our evaluation point toward the fact that while KAN-based architectures perform in line with the original claims, it may often be important to employ more complex functions on the network edges to retain the performance advantage of KANs on more complex visual data.