Pith. sign in

REVIEW 10 cited by

Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studies

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.01092 v1 pith:4WKRZJFH submitted 2024-07-01 cs.CV cs.AIcs.LG

Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studies

Ivan Drokin This is my paper
classification cs.CV cs.AIcs.LG
keywords convolutionalkansdesignkolmogorov-arnoldlayersmodelstaskscomputer
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition

    cs.CV 2026-04 unverdicted novelty 7.0

    KAConvNet introduces a Kolmogorov-Arnold Convolutional Layer to build networks competitive with ViTs and CNNs while offering stronger theoretical interpretability.

  2. KANEL\'E: Kolmogorov-Arnold Networks for Efficient LUT-based Evaluation

    cs.AR 2025-12 conditional novelty 7.0

    Quantized, pruned Kolmogorov-Arnold Networks can be compiled directly into FPGA lookup tables, achieving extreme latency/resource reductions and matching state-of-the-art LUT-based networks on several benchmarks.

  3. KAN-SAs: Efficient Acceleration of Kolmogorov-Arnold Networks on Systolic Arrays

    cs.AR 2025-11 conditional novelty 7.0

    A systolic-array accelerator that tabulates B-splines and exploits B-spline local support achieves ~100% PE utilization and a 2x cycle reduction for KAN inference compared with a conventional systolic array.

  4. AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers

    cs.AI 2026-07 conditional novelty 6.0

    A new 30-task benchmark shows LLM agents can improve real ML experiments through sequential hyperparameter choices, but their gains are uneven and often not retained.

  5. Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs

    cs.CV 2026-06 unverdicted novelty 6.0

    Structural KAN convolutions with shared value functions or wavelet-based adaptive filter shapes match or exceed per-edge KAN accuracy on CIFAR at 0.4M parameters.

  6. KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition

    cs.AI 2026-05 conditional novelty 6.0

    A hybrid KAN-MLP model for IMU-based human activity recognition achieves 5.33% relative macro F1 improvement over pure MLPs on eight datasets by placing KANs at input embedding and classification stages.

  7. Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition

    cs.CV 2026-04 unverdicted novelty 6.0

    Light-ResKAN reaches 99.09% accuracy on MSTAR SAR images with 82.9 times fewer FLOPs and 163.78 times fewer parameters than VGG16 by combining KAN convolutions, Gram polynomials, and channel-wise parameter sharing.

  8. KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition

    cs.AI 2026-05 unverdicted novelty 5.0

    A hybrid KAN-MLP architecture with KAN input embedding and specialized LarctanKAN classification layer yields 5.33% average macro F1 gain over pure-MLP baselines in IMU-based human activity recognition.

  9. GroupKAN: Efficient Kolmogorov-Arnold Networks via Grouped Spline Modeling

    cs.CV 2025-11 conditional novelty 5.0

    GroupKAN reduces KAN parameter scaling via intra-group spline mappings, delivering 79.80% average IoU (+1.11% over U-KAN) at 47.6% of the parameters on BUSI, GlaS, and CVC datasets.

  10. Interpretable Clinical Classification with Kolmogorov-Arnold Networks

    cs.LG 2025-09 conditional novelty 5.0

    Logistic KAN and KAAM achieve competitive or superior accuracy on clinical datasets compared to linear, tree, and neural baselines while providing built-in interpretability via symbolic forms and feature-wise decompositions.