Convolutional Kernel Networks
This work addresses the need for invariant image representations in visual recognition, offering a novel approach that bridges neural networks and kernels, though it is incremental in combining existing concepts.
The paper tackles the problem of achieving invariance in visual recognition by introducing a convolutional neural network that learns to approximate a kernel feature map, resulting in simpler architectures that achieve competitive accuracy on datasets like MNIST, CIFAR-10, and STL-10.
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.