A Multi-channel Training Method Boost the Performance

TL;DR

This paper introduces a multi-channel training method for deep convolutional neural networks that enhances performance and robustness, especially suited for embedded systems with limited memory.

Contribution

The paper proposes a novel multi-channel training procedure with dual networks and information pipelines, improving accuracy and robustness for resource-constrained devices.

Findings

Significant improvement in classification accuracy.

Enhanced robustness of the trained networks.

Effective adaptation to embedded system constraints.

Abstract

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.