End-to-End Kernel Learning with Supervised Convolutional Kernel Networks
This work addresses the challenge of decoupling data representation from prediction in kernel methods for image-related tasks, though it is incremental as it builds on existing convolutional kernel networks.
The paper tackles the problem of integrating kernel methods with supervised learning by developing a multilayer kernel machine that learns kernel shapes with supervision, achieving competitive performance on CIFAR-10 and SVHN for classification and image super-resolution.
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.