mlsanityData to 14 Oct 2026

Kervolutional Neural Networks

arXiv 1904.03955 ↗First posted 8 Apr 2019cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks. However, little effort has been devoted to establishing convolution in non-linear space. Existing works mainly leverage on the activation layers, which can only provide point-wise non-linearity. To solve this problem, a new operation, kervolution (kernel convolution), is introduced to approximate complex behaviors of human perception systems leveraging on the kernel trick. It generalizes convolution, enhances the model capacity, and captures higher order interactions of features, via patch-wise kernel functions, but without introducing additional parameters. Extensive experiments show that kervolutional neural networks (KNN) achieve higher accuracy and faster convergence than baseline CNN.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 4; 2023: 5; 2024: 1; 2025: 1; 2026: 1.

20 papers.

Sort:

  1. 2022B-cos Networks: Alignment is All We Need for Interpretabilitycited by 88
  2. 2021Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neuronscited by 40
  3. 2022SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensingcited by 34
  4. 2023B-cos Alignment for Inherently Interpretable CNNs and Vision Transformerscited by 31
  5. 2021On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classificationcited by 15
  6. 2021Unsupervised Online Learning for Robotic Interestingness with Visual Memorycited by 5
  7. 2021Convolutional versus Self-Organized Operational Neural Networks for Real-World Blind Image Denoisingcited by 2
  8. 2021Towards Understanding the Effectiveness of Attention Mechanismcited by 2
  9. 2022SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violencecited by 2
  10. 2023Kernel function impact on convolutional neural networkscited by 2
  11. 2023Single Domain Generalization via Normalised Cross-correlation Based Convolutionscited by 2
  12. 2024Infinite-Dimensional Feature Interactioncited by 2
8 more
  1. 2021Universal Adder Neural Networkscited by 1
  2. 2023Computational and Storage Efficient Quadratic Neurons for Deep Neural Networkscited by 1
  3. 2021IC Networks: Remodeling the Basic Unit for Convolutional Neural Networkscited by 0
  4. 2021PowerLinear Activation Functions with application to the first layer of CNNscited by 0
  5. 2022Exploring Kervolutional Neural Networkscited by 0
  6. 2023Regularized PolyKervNets: Optimizing Expressiveness and Efficiency for Private Inference in Deep Neural Networkscited by 0
  7. 2025Deformable Dynamic Convolution for Accurate yet Efficient Spatio-Temporal Traffic Predictioncited by 0
  8. 2026Learning with Volterra Neural Networks: A System Theoretic Perspectivecited by 0