Pruning-aware Sparse Regularization for Network Pruning
文献类型:期刊论文
作者 | Jiang NF(江南飞); Zhao X(赵旭); Zhao CY(赵朝阳); An YQ(安永琪); Tang M(唐明); Wang JQ(王金桥) |
刊名 | Machine Intelligence Research |
出版日期 | 2023-02 |
卷号 | 20页码:pages109–120 |
英文摘要 | Structural neural network pruning aims to remove the redundant channels in the deep convolutional neural networks (CNNs) by pruning the filters of less importance to the final output accuracy. To reduce the degradation of performance after pruning, many methods utilize the loss with sparse regularization to produce structured sparsity. In this paper, we analyze these sparsity-training-based methods and find that the regularization of unpruned channels is unnecessary. Moreover, it restricts the network’s capacity, which leads to under-fitting. To solve this problem, we propose a novel pruning method, named MaskSparsity, with pruning-aware sparse regularization. MaskSparsity imposes the fine-grained sparse regularization on the specific filters selected by a pruning mask, rather than all the filters of the model. Before the fine-grained sparse regularization of MaskSparity, we can use many methods to get the pruning mask, such as running the global sparse regularization. MaskSparsity achieves a 63.03% float point operations (FLOPs) reduction on ResNet-110 by removing 60.34% of the parameters, with no top-1 accuracy loss on CIFAR-10. On ILSVRC-2012, MaskSparsity reduces more than 51.07% FLOPs on ResNet-50, with only a loss of 0.76% in the top-1 accuracy. The code of this paper is released at https://github.com/CASIA-IVA-Lab/MaskSparsity. We have also integrated the code into a self-developed PyTorch pruning toolkit, named EasyPruner, at https://gitee.com/casia_iva_engineer/easypruner. |
源URL | [http://ir.ia.ac.cn/handle/173211/51512] |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 紫东太初大模型研究中心 |
作者单位 | 1.中国科学院大学 2.中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Jiang NF,Zhao X,Zhao CY,et al. Pruning-aware Sparse Regularization for Network Pruning[J]. Machine Intelligence Research,2023,20:pages109–120. |
APA | Jiang NF,Zhao X,Zhao CY,An YQ,Tang M,&Wang JQ.(2023).Pruning-aware Sparse Regularization for Network Pruning.Machine Intelligence Research,20,pages109–120. |
MLA | Jiang NF,et al."Pruning-aware Sparse Regularization for Network Pruning".Machine Intelligence Research 20(2023):pages109–120. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。