Convolutional Kernel Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Convolutional Kernel Networks


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.
Fichier principal
Vignette du fichier
main.pdf (233.19 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01005489 , version 1 (12-06-2014)
hal-01005489 , version 2 (02-11-2014)
hal-01005489 , version 3 (12-11-2014)



Julien Mairal, Piotr Koniusz, Zaid Harchaoui, Cordelia Schmid. Convolutional Kernel Networks. Advances in Neural Information Processing Systems (NIPS), Dec 2014, Montreal, Canada. ⟨hal-01005489v3⟩
2541 View
1948 Download



Gmail Facebook X LinkedIn More