Convolutional Kernel Networks

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

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 131 CITATIONS, ESTIMATED 42% COVERAGE

309 Citations

050100'14'15'16'17'18'19
Citations per Year
Semantic Scholar estimates that this publication has 309 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…