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… (More)


5 Figures and Tables


Citations per Year

122 Citations

Semantic Scholar estimates that this publication has 122 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Mairal2014ConvolutionalKN, title={Convolutional Kernel Networks}, author={Julien Mairal and Piotr Koniusz and Za{\"{i}d Harchaoui and Cordelia Schmid}, booktitle={NIPS}, year={2014} }