A Multi-channel Training Method Boost the Performance
This work addresses the need for efficient neural networks on mobile devices, but appears incremental as it builds on existing methods for network scaling.
The authors tackled the problem of adapting deep convolutional neural networks to embedded systems with limited memory by proposing a multi-channel training procedure, which enhanced classification accuracy and robustness.
Deep convolutional neural network has made huge revolution and shown its superior performance on computer vision tasks such as classification and segmentation. Recent years, researches devote much effort to scaling down size of network while maintaining its ability, to adapt to the limited memory on embedded systems like mobile phone. In this paper, we propose a multi-channel training procedure which can highly facilitate the performance and robust of the target network. The proposed procedure contains two sets of networks and two information pipelines which can work independently hinge on the computation ability of the embedded platform, while in the mean time, the classification accuracy is also admirably enhanced.