Cascaded Coarse-to-Fine Deep Kernel Networks for Efficient Satellite Image Change Detection
This work addresses efficiency issues in deep kernel networks for satellite image analysis, which is incremental as it builds on existing methods to improve computational performance.
The paper tackles the computational complexity of deep kernel networks for satellite image change detection by proposing a coarse-to-fine cascade framework that reduces evaluation complexity while maintaining accuracy, achieving high efficiency in experiments on large satellite images.
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.