Image embeddings with Kolmogorov-Arnold networks
Loading...
Date
2025
Authors
Юрченко, Артур
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This research aims to evaluate performance of Kolmogorov-Arnold networks (KAN) in image embedding tasks. It focuses on modifying existing state-of-the-art architectures - CNN and ViT, replacing their MLP segments with KANs, aiming to improve their computational performance and embedding quality. Training and evaluation methodology is fully described in sections 4 and 5.
Description
Keywords
Kolmogorov-Arnold networks, Computer Vision, Embedding, Convolutional neural networks, Vision Transformers, Encoders, Classification, Regression, Retrieval, Interpretability, bachelor`s thesis