CHIP: CHannel Independence-based Pruning for Compact Neural Networks

Abstract

Filter pruning has been widely used for neural network compression because of its enabled practical acceleration. To date, most of the existing filter pruning works explore the importance of filters via using intra-channel information. In this paper, starting from an inter-channel perspective, we propose to perform efficient filter pruning using Channel Independence, a metric that measures the correlations among different feature maps. The less independent feature map is interpreted as containing less useful information$/$knowledge, and hence its corresponding filter can be pruned without affecting model capacity. We systematically investigate the quantification metric, measuring scheme and sensitiveness$/$reliability of channel independence in the context of filter pruning. Our evaluation results for different models on various datasets show the superior performance of our approach. Notably, on CIFAR-10 dataset our solution can bring $0.90\%$ and $0.94\%$ accuracy increase over baseline ResNet-56 and ResNet-110 models, respectively, and meanwhile the model size and FLOPs are reduced by $42.8\%$ and $47.4\%$ (for ResNet-56) and $48.3\%$ and $52.1\%$ (for ResNet-110), respectively. On ImageNet dataset, our approach can achieve $40.8\%$ and $44.8\%$ storage and computation reductions, respectively, with $0.15\%$ accuracy increase over the baseline ResNet-50 model. The code is available at https://github.com/Eclipsess/CHIP_NeurIPS2021.

Accepted by NeurIPS 2021. Model Compression, Channel Pruning, Filter Pruning, Deep Learning

References in corpus (8)

• Distilling the Knowledge in a Neural Network
• Pruning Filters for Efficient ConvNets
• Dynamic Network Surgery for Efficient DNNs
• Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization
• Dynamic Model Pruning with Feedback
• Tensor-Train Recurrent Neural Networks for Video Classification
• ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations
• Compressing Recurrent Neural Networks Using Hierarchical Tucker Tensor Decomposition

Cited by in corpus (4)

• Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications
• HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks
• Pruning-aware Sparse Regularization for Network Pruning
• Neural network relief: a pruning algorithm based on neural activity