Cascaded Coarse-to-Fine Deep Kernel Networks for Efficient Satellite Image Change Detection

Abstract

Deep networks are nowadays becoming popular in many computer vision and pattern recognition tasks. Among these networks, deep kernels are particularly interesting and effective, however, their computational complexity is a major issue especially on cheap hardware resources. In this paper, we address the issue of efficient computation in deep kernel networks. We propose a novel framework that reduces dramatically the complexity of evaluating these deep kernels. Our method is based on a coarse-to-fine cascade of networks designed for efficient computation; early stages of the cascade are cheap and reject many patterns efficiently while deep stages are more expensive and accurate. The design principle of these reduced complexity networks is based on a variant of the cross-entropy criterion that reduces the complexity of the networks in the cascade while preserving all the positive responses of the original kernel network. Experiments conducted - on the challenging and time demanding change detection task, on very large satellite images - show that our proposed coarse-to-fine approach is effective and highly efficient.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Learning Structured Sparsity in Deep Neural Networks
• Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
• The Power of Sparsity in Convolutional Neural Networks
• Deep Multiple Kernel Learning
• Speeding up Convolutional Neural Networks By Exploiting the Sparsity of Rectifier Units
• A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation