Learning compact ConvNets through filter pruning based on the saliency of a feature map
Open Access
- 12 September 2021
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 16 (1), 123-133
- https://doi.org/10.1049/ipr2.12338
Abstract
With the performance increase of convolutional neural network (CNN), the disadvantages of CNN's high storage and high power consumption are followed. Among the methods mentioned in various literature, filter pruning is a crucial method for constructing lightweight networks. However, the current filter pruning method is still challenged by complicated processes and training inefficiency. This paper proposes an effective filter pruning method, which uses the saliency of the feature map (SFM), i.e. information entropy, as a theoretical guide for whether the filter is essential. The pruning principle use here is that the filter with a weak saliency feature map in the early stage will not significantly improve the final accuracy. Thus, one can efficiently prune the non-salient feature map with a smaller information entropy and the corresponding filter. Besides, an over-parameterized convolution method is employed to improve the pruned model's accuracy without increasing parameter at inference time. Experimental results show that without introducing any additional constraints, the effectiveness of this method in FLOPs and parameters reduction with similar accuracy has advanced the state-of-the-art. For example, on CIFAR-10, the pruned VGG-16 achieves only a small loss of 0.39% in Top-1 accuracy with a factor of 83.3% parameters, and 66.7% FLOPs reductions. On ImageNet-100, the pruned ResNet-50 achieves only a small accuracy degradation of 0.76% in Top-1 accuracy with a factor of 61.19% parameters, and 62.98% FLOPs reductions.Keywords
Funding Information
- National Natural Science Foundation of China (61772576, 62072489, U1804157)
This publication has 32 references indexed in Scilit:
- You Only Look Once: Unified, Real-Time Object DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Fast R-CNNPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- U-Net: Convolutional Networks for Biomedical Image SegmentationPublished by Springer Science and Business Media LLC ,2015
- Efficient and accurate approximations of nonlinear convolutional networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Going deeper with convolutionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Fully convolutional networks for semantic segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- A CGA-MRF Hybrid Method for Iris Texture Analysis and ModelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Speeding up Convolutional Neural Networks with Low Rank ExpansionsPublished by British Machine Vision Association and Society for Pattern Recognition ,2014
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989