mlsanityData to 7 Oct 2026

Suitability of KANs for Computer Vision: A preliminary investigation

arXiv 2406.09087 ↗First posted 13 Jun 2024cs.CV cs.AIcited by 33

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 13 Jun 2024.

Builds on

14 of 35 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  9. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  10. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  11. 2024U-KAN Makes Strong Backbone for Medical Image Segmentation and Generationcited by 176
  12. 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 118
2 more
  1. 2024Kolmogorov-Arnold Networks (KANs) for Time Series Analysiscited by 97
  2. 2020The Kolmogorov-Arnold representation theorem revisitedcited by 89

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 21; 2025: 10; 2026: 2.

33 papers.

Sort:

  1. 2024KAN 2.0: Kolmogorov-Arnold Networks Meet Sciencecited by 116
  2. 2024Adaptive Training of Grid-Dependent Physics-Informed Kolmogorov-Arnold Networkscited by 37
  3. 2024On the expressiveness and spectral bias of KANscited by 36
  4. 2024Finite basis Kolmogorov-Arnold networks: domain decomposition for data-driven and physics-informed problemscited by 35
  5. 2024rKAN: Rational Kolmogorov-Arnold Networkscited by 31
  6. 2024Reduced Effectiveness of Kolmogorov-Arnold Networks on Functions with Noisecited by 17
  7. 2024PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Setscited by 15
  8. 2024DropKAN: Regularizing KANs by masking post-activationscited by 14
  9. 2024Generalization Bounds and Model Complexity for Kolmogorov-Arnold Networkscited by 11
  10. 2024Multifidelity Kolmogorov-Arnold Networkscited by 9
  11. 2024CF-KAN: Kolmogorov-Arnold Network-based Collaborative Filtering to Mitigate Catastrophic Forgetting in Recommender Systemscited by 8
  12. 2024DKL-KAN: Scalable Deep Kernel Learning using Kolmogorov-Arnold Networkscited by 7
21 more
  1. 2024KAN versus MLP on Irregular or Noisy Functionscited by 7
  2. 2025Kolmogorov-Arnold Recurrent Network for Short Term Load Forecasting Across Diverse Consumerscited by 7
  3. 2024Rethinking the Function of Neurons in KANscited by 5
  4. 2024KAN we improve on HEP classification tasks? Kolmogorov-Arnold Networks applied to an LHC physics examplecited by 4
  5. 2024Incorporating Arbitrary Matrix Group Equivariance into KANscited by 4
  6. 2024On Training of Kolmogorov-Arnold Networkscited by 4
  7. 2024GNN-SKAN: Harnessing the Power of SwallowKAN to Advance Molecular Representation Learning with GNNscited by 3
  8. 2025Physics-informed KAN PointNet: Deep learning for simultaneous solutions to inverse problems in incompressible flow on numerous irregular geometriescited by 3
  9. 2025Conformalized-KANs: Uncertainty Quantification with Coverage Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learningcited by 3
  10. 2025EHCTNet: Enhanced Hybrid of CNN and Transformer Network for Remote Sensing Image Change Detectioncited by 2
  11. 2025Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?cited by 2
  12. 2025Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Modelscited by 2
  13. 2024Kaninfradet3D:A Road-side Camera-LiDAR Fusion 3D Perception Model based on Nonlinear Feature Extraction and Intrinsic Correlationcited by 1
  14. 2024KAT to KANs: A Review of Kolmogorov-Arnold Networks and the Neural Leap Forwardcited by 1
  15. 2025Advancing Out-of-Distribution Detection via Local Neuroplasticitycited by 1
  16. 2026RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basiscited by 1
  17. 2024DP-KAN: Differentially Private Kolmogorov-Arnold Networkscited by 0
  18. 2025Semi-KAN: KAN Provides an Effective Representation for Semi-Supervised Learning in Medical Image Segmentationcited by 0
  19. 2025"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understandingcited by 0
  20. 2025KAConvText: Novel Approach to Burmese Sentence Classification using Kolmogorov-Arnold Convolutioncited by 0
  21. 2026ABFR-KAN: Kolmogorov-Arnold Networks for Functional Brain Analysiscited by 0