SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners

Abstract

Deep Convolutional Neural Networks (CNN) has achieved significant success in computer vision field. However, the high computational cost of the deep complex models prevents the deployment on edge devices with limited memory and computational resource. In this paper, we proposed a novel filter pruning for convolutional neural networks compression, namely spectral clustering filter pruning with soft self-adaption manners (SCSP). We first apply spectral clustering on filters layer by layer to explore their intrinsic connections and only count on efficient groups. By self-adaption manners, the pruning operations can be done in few epochs to let the network gradually choose meaningful groups. According to this strategy, we not only achieve model compression while keeping considerable performance, but also find a novel angle to interpret the model compression process.

References in corpus (8)

• Distilling the Knowledge in a Neural Network
• FitNets: Hints for Thin Deep Nets
• Pruning Convolutional Neural Networks for Resource Efficient Inference
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Pruning Filters for Efficient ConvNets
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Convolutional neural networks with low-rank regularization
• NISP: Pruning Networks using Neuron Importance Score Propagation

Cited by in corpus (6)

• Filter Pruning by Switching to Neighboring CNNs with Good Attributes
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration
• Functionality-Oriented Convolutional Filter Pruning
• Filter Grafting for Deep Neural Networks
• Filter Grafting for Deep Neural Networks: Reason, Method, and Cultivation