Channel Pruning Guided by Classification Loss and Feature Importance
arXiv:2003.06757
Abstract
In this work, we propose a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI). In contrast to the existing layer-by-layer channel pruning approaches that only consider how to reconstruct the features from the next layer, our approach additionally take the classification loss into account in the channel pruning process. We also observe that some reconstructed features will be removed at the next pruning stage. So it is unnecessary to reconstruct these features. To this end, we propose a new strategy to suppress the influence of unimportant features (i.e., the features will be removed at the next pruning stage). Our comprehensive experiments on three benchmark datasets, i.e., CIFAR-10, ImageNet, and UCF-101, demonstrate the effectiveness of our CPLI method.
arXiv commentAAAI2020
References in corpus (9)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- Compressing Deep Convolutional Networks using Vector Quantization
- Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
- Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
- PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions