paper-with-me

홈 › Papers

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

2016-05-20 · NeurIPS 2016 12 · Julien Mairal

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.

📄 PDF Abstract BibTeX arXiv:1605.06265

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationImage Super-ResolutionSuper-Resolution

Similar Papers 제목 키워드 기반

An End-to-End Graph Convolutional Kernel Support Vector Machine

2020-02-29 · Padraig Corcoran

A novel kernel-based support vector machine (SVM) for graph classification is proposed. The SVM feature space mapping consists of a sequence of graph convolutional layers, which generates a vector space representation fo…

ClassificationFeature EngineeringGeneral ClassificationGraph Classification

Convolutional Kernel Networks for Graph-Structured Data

2020-03-11 · ICML 2020 1 · Dexiong Chen, Laurent Jacob, Julien Mairal

We introduce a family of multilayer graph kernels and establish new links between graph convolutional neural networks and kernel methods. Our approach generalizes convolutional kernel networks to graph-structured data, b…

Graph Classification

The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods

2021-01-19 · Louis Thiry, Michael Arbel, Eugene Belilovsky, Edouard Oyallon

A recent line of work showed that various forms of convolutional kernel methods can be competitive with standard supervised deep convolutional networks on datasets like CIFAR-10, obtaining accuracies in the range of 87-9…

Object RecognitionRepresentation Learning

The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods.

2021-01-01 · ICLR 2021 1 · Louis Thiry, Michael Arbel, Eugene Belilovsky, Edouard Oyallon

A recent line of work showed that various forms of convolutional kernel methods can be competitive with standard supervised deep convolutional networks on datasets like CIFAR-10, obtaining accuracies in the range of 87…

Object RecognitionRepresentation Learning

Orthogonal Convolutional Neural Networks

2019-11-27 · CVPR 2020 6 · Jiayun Wang, Yubei Chen, Rudrasis Chakraborty, Stella X. Yu

Deep convolutional neural networks are hindered by training instability and feature redundancy towards further performance improvement. A promising solution is to impose orthogonality on convolutional filters. We develop…

image-classificationImage ClassificationImage Retrieval