Deep Learning with Kernel Regularization for Visual Recognition

In this paper we focus on training deep neural networks for visual recognition tasks. One challenge is the lack of an informative regularization on the network parameters, to imply a meaningful control on the computed function. We propose a training strategy that takes advantage of kernel methods, where an existing kernel function represents useful prior knowledge about the learning task of interest. We derive an efficient algorithm using stochastic gradient descent, and demonstrate very positive results in a wide range of visual recognition tasks.

Authors

• Kai Yu Shanghai Jiao Tong University
• Wei Xu Georgia Institute of Technology
• Yihong Gong Xi'an Jiaotong University Shenzhen University of Advanced Technology

Keywords

No keywords are indexed for this paper.