mlsanityData to 7 Oct 2026

Exploring Kolmogorov-Arnold networks for realistic image sharpness assessment

arXiv 2409.07762 ↗First posted 12 Sep 2024cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Score prediction is crucial in evaluating realistic image sharpness based on collected informative features. Recently, Kolmogorov-Arnold networks (KANs) have been developed and witnessed remarkable success in data fitting. This study introduces the Taylor series-based KAN (TaylorKAN). Then, different KANs are explored in four realistic image databases (BID2011, CID2013, CLIVE, and KonIQ-10k) to predict the scores by using 15 mid-level features and 2048 high-level features. Compared to support vector regression, results show that KANs are generally competitive or superior, and TaylorKAN is the best one when mid-level features are used. This is the first study to investigate KANs on image quality assessment that sheds some light on how to select and further improve KANs in related tasks.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 17 of its 36 references that are in the map. First posted on arXiv 12 Sep 2024.

Builds on

17 of 36 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  4. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  5. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 276
  6. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 208
  7. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
  8. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
  9. 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 118
  10. 2024KAN 2.0: Kolmogorov-Arnold Networks Meet Sciencecited by 116
  11. 2024Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximationcited by 115
  12. 2020The Kolmogorov-Arnold representation theorem revisitedcited by 89
5 more
  1. 2021Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Trainingcited by 71
  2. 2024fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functionscited by 60
  3. 2024BSRBF-KAN: A combination of B-splines and Radial Basis Functions in Kolmogorov-Arnold Networkscited by 43
  4. 2024Enhancing Graph Collaborative Filtering with FourierKAN Feature Transformationcited by 41
  5. 2022REQA: Coarse-to-fine Assessment of Image Quality to Alleviate the Range Effectcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2026Vision KAN: Towards an Attention-Free Backbone for Vision with Kolmogorov-Arnold Networkscited by 2
  2. 2025Efficiency Bottlenecks of Convolutional Kolmogorov-Arnold Networks: A Comprehensive Scrutiny with ImageNet, AlexNet, LeNet and Tabular Classificationcited by 1
  3. 2025Taylor expansion-based Kolmogorov-Arnold network for blind image quality assessmentcited by 1
  4. 2026Ultra-High-Definition Image Quality Assessment via Graph Representation Learningcited by 0
  5. 2026STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecastingcited by 0