Towards More Efficient and Effective Inference: The Joint Decision of Multi-Participants
This addresses the need for efficient neural networks on resource-constrained edge devices, but it is incremental as it builds on existing compression and optimization techniques.
The paper tackles the problem of deploying neural networks on edge devices by proposing a method that improves inference efficiency and effectiveness without significantly increasing model size, achieving up to 0.26% higher accuracy on CIFAR-10 and 4.49% on CIFAR-100 with similar parameters.
Existing approaches to improve the performances of convolutional neural networks by optimizing the local architectures or deepening the networks tend to increase the size of models significantly. In order to deploy and apply the neural networks to edge devices which are in great demand, reducing the scale of networks are quite crucial. However, It is easy to degrade the performance of image processing by compressing the networks. In this paper, we propose a method which is suitable for edge devices while improving the efficiency and effectiveness of inference. The joint decision of multi-participants, mainly contain multi-layers and multi-networks, can achieve higher classification accuracy (0.26% on CIFAR-10 and 4.49% on CIFAR-100 at most) with similar total number of parameters for classical convolutional neural networks.