Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studies

• URL: http://arxiv.org/abs/2407.01092v1
• Date: Mon, 1 Jul 2024 08:49:33 GMT
• Title: Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studies
• Authors: Ivan Drokin,
• Abstract summary: This paper explores the application of Kolmogorov-Arnold Networks (KANs) in the domain of computer vision (CV) We propose a parameter-efficient design for Kolmogorov-Arnold convolutional layers and a parameter-efficient finetuning algorithm for pre-trained KAN models. We provide empirical evaluations conducted on MNIST, CIFAR10, CIFAR100, Tiny ImageNet, ImageNet1k, and HAM10000 datasets for image classification tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The emergence of Kolmogorov-Arnold Networks (KANs) has sparked significant interest and debate within the scientific community. This paper explores the application of KANs in the domain of computer vision (CV). We examine the convolutional version of KANs, considering various nonlinearity options beyond splines, such as Wavelet transforms and a range of polynomials. We propose a parameter-efficient design for Kolmogorov-Arnold convolutional layers and a parameter-efficient finetuning algorithm for pre-trained KAN models, as well as KAN convolutional versions of self-attention and focal modulation layers. We provide empirical evaluations conducted on MNIST, CIFAR10, CIFAR100, Tiny ImageNet, ImageNet1k, and HAM10000 datasets for image classification tasks. Additionally, we explore segmentation tasks, proposing U-Net-like architectures with KAN convolutions, and achieving state-of-the-art results on BUSI, GlaS, and CVC datasets. We summarized all of our findings in a preliminary design guide of KAN convolutional models for computer vision tasks. Furthermore, we investigate regularization techniques for KANs. All experimental code and implementations of convolutional layers and models, pre-trained on ImageNet1k weights are available on GitHub via this https://github.com/IvanDrokin/torch-conv-kan

Related papers

• KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements [1.663204995903499]
  We introduce KANICE, a novel neural architecture that combines Convolutional Neural Networks (CNNs) with Kolmogorov-Arnold Network (KAN) principles. KANICE integrates Interactive Convolutional Blocks (ICBs) and KAN linear layers into a CNN framework. We evaluated KANICE on four datasets: MNIST, Fashion-MNIST, EMNIST, and SVHN.
  arXiv  Detail & Related papers  (2024-10-22T16:50:34Z)
• Kolmogorov-Arnold Network Autoencoders [0.0]
  Kolmogorov-Arnold Networks (KANs) are promising alternatives to Multi-Layer Perceptrons (MLPs) KANs align closely with the Kolmogorov-Arnold representation theorem, potentially enhancing both model accuracy and interpretability. Our results demonstrate that KAN-based autoencoders achieve competitive performance in terms of reconstruction accuracy.
  arXiv  Detail & Related papers  (2024-10-02T22:56:00Z)
• Convolutional Kolmogorov-Arnold Networks [41.94295877935867]
  We introduce Convolutional Kolmogorov-Arnold Networks (Convolutional KANs) In this paper, we empirically validate the performance of Convolutional KANs against traditional architectures across Fashion-MNIST dataset. Experiments show that KAN Convolutions seem to learn more per kernel, which opens up a new horizon of possibilities in deep learning for computer vision.
  arXiv  Detail & Related papers  (2024-06-19T02:09:44Z)
• U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation [48.40120035775506]
  Kolmogorov-Arnold Networks (KANs) reshape the neural network learning via the stack of non-linear learnable activation functions. We investigate, modify and re-design the established U-Net pipeline by integrating the dedicated KAN layers on the tokenized intermediate representation, termed U-KAN. We further delved into the potential of U-KAN as an alternative U-Net noise predictor in diffusion models, demonstrating its applicability in generating task-oriented model architectures.
  arXiv  Detail & Related papers  (2024-06-05T04:13:03Z)
• Neural Clustering based Visual Representation Learning [61.72646814537163]
  Clustering is one of the most classic approaches in machine learning and data analysis. We propose feature extraction with clustering (FEC), which views feature extraction as a process of selecting representatives from data. FEC alternates between grouping pixels into individual clusters to abstract representatives and updating the deep features of pixels with current representatives.
  arXiv  Detail & Related papers  (2024-03-26T06:04:50Z)
• How to Train Neural Field Representations: A Comprehensive Study and Benchmark [29.725680049946032]
  We propose a JAX-based library that leverages parallelization to enable fast optimization of datasets of neural fields. We perform a study that investigates the effects of different hyper parameters on fitting NeFs for downstream tasks. Based on the proposed library and our analysis, we propose Neural Field Arena, a benchmark consisting of neural field variants of popular vision datasets.
  arXiv  Detail & Related papers  (2023-12-16T20:10:23Z)
• A new perspective on probabilistic image modeling [92.89846887298852]
  We present a new probabilistic approach for image modeling capable of density estimation, sampling and tractable inference. DCGMMs can be trained end-to-end by SGD from random initial conditions, much like CNNs. We show that DCGMMs compare favorably to several recent PC and SPN models in terms of inference, classification and sampling.
  arXiv  Detail & Related papers  (2022-03-21T14:53:57Z)
• A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP [121.35904748477421]
  Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision. Transformer and multi-layer perceptron (MLP)-based models, such as Vision Transformer and Vision-Mixer, started to lead new trends. In this paper, we conduct empirical studies on these DNN structures and try to understand their respective pros and cons.
  arXiv  Detail & Related papers  (2021-08-30T06:09:02Z)
• PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer [76.44375136492827]
  Convolutional Neural Networks (CNNs) are often scale-sensitive. We bridge this regret by exploiting multi-scale features in a finer granularity. The proposed convolution operation, named Poly-Scale Convolution (PSConv), mixes up a spectrum of dilation rates.
  arXiv  Detail & Related papers  (2020-07-13T05:14:11Z)
• Binarizing MobileNet via Evolution-based Searching [66.94247681870125]
  We propose a use of evolutionary search to facilitate the construction and training scheme when binarizing MobileNet. Inspired by one-shot architecture search frameworks, we manipulate the idea of group convolution to design efficient 1-Bit Convolutional Neural Networks (CNNs) Our objective is to come up with a tiny yet efficient binary neural architecture by exploring the best candidates of the group convolution.
  arXiv  Detail & Related papers  (2020-05-13T13:25:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.