Coarse and fine-grained automatic cropping deep convolutional neural network

Abstract

The existing convolutional neural network pruning algorithms can be divided into two categories: coarse-grained clipping and fine-grained clipping. This paper proposes a coarse and fine-grained automatic pruning algorithm, which can achieve more efficient and accurate compression acceleration for convolutional neural networks. First, cluster the intermediate feature maps of the convolutional neural network to obtain the network structure after coarse-grained clipping, and then use the particle swarm optimization algorithm to iteratively search and optimize the structure. Finally, the optimal network tailoring substructure is obtained.

arXiv comment12 pages, 1 table

References in corpus (8)

• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Neural Architecture Search with Reinforcement Learning
• AMC: AutoML for Model Compression and Acceleration on Mobile Devices
• Rethinking the Value of Network Pruning
• SNIP: Single-shot Network Pruning based on Connection Sensitivity
• XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
• Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning