mlsanityData to 14 Oct 2026

Convolutional Kernel Networks

arXiv 1406.3332 ↗First posted 12 Jun 2014cs.CV cs.LG stat.MLcited by 47

Not on the map. Why?

Abstract (arXiv)

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is encoded by a reproducing kernel. Unlike traditional approaches where neural networks are learned either to represent data or for solving a classification task, our network learns to approximate the kernel feature map on training data. Such an approach enjoys several benefits over classical ones. First, by teaching CNNs to be invariant, we obtain simple network architectures that achieve a similar accuracy to more complex ones, while being easy to train and robust to overfitting. Second, we bridge a gap between the neural network literature and kernels, which are natural tools to model invariance. We evaluate our methodology on visual recognition tasks where CNNs have proven to perform well, e.g., digit recognition with the MNIST dataset, and the more challenging CIFAR-10 and STL-10 datasets, where our accuracy is competitive with the state of the art.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Jun 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 10; 2023: 6; 2024: 6; 2025: 5; 2026: 7.

47 papers.

Sort:

By area:

  1. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  2. 2021On Aliased Resizing and Surprising Subtleties in GAN Evaluationcited by 51
  3. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  4. 2021Approximation and Learning with Deep Convolutional Models: a Kernel Perspectivecited by 31
  5. 2021Learning with convolution and pooling operations in kernel methodscited by 21
  6. 2022Fast Neural Kernel Embeddings for General Activationscited by 18
  7. 2023A Rainbow in Deep Network Black Boxescited by 18
  8. 2022On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernelscited by 16
  9. 2021On the Sample Complexity of Learning under Invariance and Geometric Stabilitycited by 13
  10. 2023Regularization of polynomial networks for image recognitioncited by 13
  11. 2022Graph-adaptive Rectified Linear Unit for Graph Neural Networkscited by 12
  12. 2022A Kernel-Expanded Stochastic Neural Networkcited by 9
35 more
  1. 2021The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methodscited by 8
  2. 2021Deformation Robust Roto-Scale-Translation Equivariant CNNscited by 7
  3. 2022Learning in RKHM: a C^*-Algebraic Twist for Kernel Machinescited by 7
  4. 2023Deep Learning with Kernels through RKHM and the Perron-Frobenius Operatorcited by 7
  5. 2023Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Spacecited by 5
  6. 2024Descriptive Kernel Convolution Network with Improved Random Walk Kernelcited by 5
  7. 2025Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learningcited by 5
  8. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4
  9. 2021Correlated Weights in Infinite Limits of Deep Convolutional Neural Networkscited by 3
  10. 2023Convolutional Deep Kernel Machinescited by 3
  11. 2025Feature Hallucination for Self-supervised Action Recognitioncited by 3
  12. 2021Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representationscited by 2
  13. 2021Structured Convolutional Kernel Networks for Airline Crew Schedulingcited by 2
  14. 2021Convolutional Motif Kernel Networkscited by 2
  15. 2022Deep Layer-wise Networks Have Closed-Form Weightscited by 2
  16. 2024Infinite-Dimensional Feature Interactioncited by 2
  17. 2021Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scalescited by 1
  18. 2022Dual Convexified Convolutional Neural Networkscited by 1
  19. 2022COmic: Convolutional Kernel Networks for Interpretable End-to-End Learning on (Multi-)Omics Datacited by 1
  20. 2024Efficient Visual Representation Learning with Heat Conduction Equationcited by 1
  21. 2024Exploring Consistency in Graph Representations:from Graph Kernels to Graph Neural Networkscited by 1
  22. 2025Optimal Density Functions for Weighted Convolution in Learning Modelscited by 1
  23. 2025Optimal Weighted Convolution for Classification and Denosingcited by 1
  24. 2025Operator-Based Generalization Bound for Deep Learning: Insights on Multi-Task Learningcited by 1
  25. 2026Classifying several dialectal Nawatl varietiescited by 1
  26. 2026Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignmentcited by 1
  27. 2026A Universal Reproducing Kernel Hilbert Space from Polynomial Alignment and IMQ Distancecited by 1
  28. 2021Neural Generalization of Multiple Kernel Learningcited by 0
  29. 2022Measuring dissimilarity with diffeomorphism invariancecited by 0
  30. 2024Stability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNscited by 0
  31. 2024Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machinescited by 0
  32. 2026Beyond Convolution: A Taxonomy of Structured Operators for Learning-Based Image Processingcited by 0
  33. 2026No More DeLuLu: Physics-Inspired Kernel Networks for Geometrically-Grounded Neural Computationcited by 0
  34. 2026End-to-End Neural Decomposition with Koopman Operators for Time-Series Forecastingcited by 0
  35. 2026Theory Guided and Interpretable Neural Operator Design for Partial Differential Equation Learningcited by 0