Deep representation design from deep kernel networks

Mingyuan Jiu

doi:10.1016/j.patcog.2018.12.005

Return

Deep representation design from deep kernel networks

2019-04-01

酒明远 (Mingyuan Jiu) *

Hichem Sahbi

DOI：10.1016/j.patcog.2018.12.005

Original

Save

View PDF

Abstract

En 中文

Deep kernel learning aims at designing nonlinear combinations of multiple standard elementary kernels by training deep networks. This scheme has proven to be effective, but intractable when handling large-scale datasets especially when the depth of the trained networks increases; indeed, the complexity of evaluating these networks scales quadratically w.r.t. the size of training data and linearly w.r.t. the depth of the trained networks. In this paper, we address the issue of efficient computation in Deep Kernel Networks (DKNs) by designing effective maps in the underlying Reproducing Kernel Hilbert Spaces (RKHS). Given a pretrained DKN, our method builds its associated Deep Map Network (DMN) whose inner product approximates the original network while being far more efficient. The design principle of our method is greedy and achieved layer-wise, by finding maps that approximate DKNs at different (input, intermediate and output) layers. This design also considers an extra fine-tuning step based on unsupervised learning, that further enhances the generalization ability of the trained DMNs. When plugged into SVMs, these DMNs turn out to be as accurate as the underlying DKNs while being at least an order of magnitude faster on large-scale datasets, as shown through extensive experiments on the challenging ImageCLEF, COREL5k benchmarks and the Banana dataset. (C) 2018 Elsevier Ltd. All rights reserved.

Keywords:

Multiple kernel learning

Kernel design

Deep networks

Efficient computation

Image annotation

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.