Abstract
Multiple kernel learning (MKL) is a widely used technique for kernel design. Its principle consists in learning, for a given support vector classifier, the most suitable convex (or sparse) linear combination of standard elementary kernels. However, these combinations are shallow and often powerless to capture the actual similarity between highly semantic data, especially for challenging classification tasks, such as image annotation. In this paper, we redefine multiple kernels using deep multi-layer networks. In this new contribution, a deep multiple kernel is recursively defined as a multi-layered combination of nonlinear activation functions, each one involves a combination of several elementary or intermediate kernels, and results into a positive semi-definite deep kernel. We propose four different frameworks in order to learn the weights of these networks: supervised, unsupervised, kernel-based semi-supervised, and Laplacian-based semi-supervised. When plugged into support vector machines, the resulting deep kernel networks show clear gain, compared with several shallow kernels for the task of image annotation. Extensive experiments and analysis on the challenging ImageCLEF photo annotation benchmark, the COREL5k database, and the Banana data set validate the effectiveness of the proposed method.
Funding Information
  • Research Agency Agence Nationale de la Recherche under the MLVIS Project (ANR-11-BS02-0017)

This publication has 39 references indexed in Scilit: