mlsanityData to 14 Oct 2026

End-to-End Kernel Learning with Supervised Convolutional Kernel Networks

arXiv 1605.06265 ↗First posted 20 May 2016stat.ML cs.CV cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce a new image representation based on a multilayer kernel machine. Unlike traditional kernel methods where data representation is decoupled from the prediction task, we learn how to shape the kernel with supervision. We proceed by first proposing improvements of the recently-introduced convolutional kernel networks (CKNs) in the context of unsupervised learning; then, we derive backpropagation rules to take advantage of labeled training data. The resulting model is a new type of convolutional neural network, where optimizing the filters at each layer is equivalent to learning a linear subspace in a reproducing kernel Hilbert space (RKHS). We show that our method achieves reasonably competitive performance for image classification on some standard "deep learning" datasets such as CIFAR-10 and SVHN, and also for image super-resolution, demonstrating the applicability of our approach to a large variety of image-related tasks.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 8; 2023: 6; 2024: 3; 2025: 2; 2026: 1.

28 papers.

Sort:

By area:

  1. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  2. 2021Approximation and Learning with Deep Convolutional Models: a Kernel Perspectivecited by 31
  3. 2021Locality defeats the curse of dimensionality in convolutional teacher-student scenarioscited by 26
  4. 2021Learning with convolution and pooling operations in kernel methodscited by 21
  5. 2023A Rainbow in Deep Network Black Boxescited by 18
  6. 2022On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernelscited by 16
  7. 2023Regularization of polynomial networks for image recognitioncited by 13
  8. 2021The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methodscited by 8
  9. 2022On the Benefits of Large Learning Rates for Kernel Methodscited by 8
  10. 2021Deformation Robust Roto-Scale-Translation Equivariant CNNscited by 7
  11. 2022Learning in RKHM: a C^*-Algebraic Twist for Kernel Machinescited by 7
  12. 2024Descriptive Kernel Convolution Network with Improved Random Walk Kernelcited by 5
16 more
  1. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4
  2. 2023Convolutional Deep Kernel Machinescited by 3
  3. 2025MoSE: Unveiling Structural Patterns in Graphs via Mixture of Subgraph Expertscited by 3
  4. 2021Structured Convolutional Kernel Networks for Airline Crew Schedulingcited by 2
  5. 2021Convolutional Motif Kernel Networkscited by 2
  6. 2022Generalized Reference Kernel for One-class Classificationcited by 2
  7. 2022Frequency Dropout: Feature-Level Regularization via Randomized Filteringcited by 2
  8. 2023Higher Order Gauge Equivariant CNNs on Riemannian Manifolds and Applicationscited by 2
  9. 2022OTFPF: Optimal Transport-Based Feature Pyramid Fusion Network for Brain Age Estimation with 3D Overlapped ConvNeXtcited by 1
  10. 2022COmic: Convolutional Kernel Networks for Interpretable End-to-End Learning on (Multi-)Omics Datacited by 1
  11. 2026Tunneling the Loss Landscape: Bypassing Memorization with Monte Carlo Parameter Swappingcited by 1
  12. 2021Neural Generalization of Multiple Kernel Learningcited by 0
  13. 2023On Inductive Biases for Machine Learning in Data Constrained Settingscited by 0
  14. 2024Stability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNscited by 0
  15. 2024Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machinescited by 0
  16. 2025L2GNet: Optimal Local-to-Global Representation of Anatomical Structures for Generalized Medical Image Segmentationcited by 0