QSFM: Model Pruning Based on Quantified Similarity Between Feature Maps for AI on Edge
文献类型：期刊论文
| 作者 | Wang, Zidu1,2; Liu, Xuexin1,2; Huang, Long2; Chen, Yunqing2; Zhang, Yufei2; Lin, Zhikang2; Wang, Rui2
|
| 刊名 | IEEE INTERNET OF THINGS JOURNAL
 |
| 出版日期 | 2022-12-01 |
| 卷号 | 9期号:23页码:24506-24515 |
| 关键词 | Tensors Internet of Things Convolution Three-dimensional displays Quantization (signal) Hardware Training Edge computing filter pruning Internet of Things (IoT) model compression neural networks |
| ISSN号 | 2327-4662 |
| DOI | 10.1109/JIOT.2022.3190873 |
| 通讯作者 | Wang, Rui(wangrui@ustb.edu.cn) |
| 英文摘要 | Convolutional neural networks (CNNs) have been applied in numerous Internet of Things (IoT) devices for multifarious downstream tasks. However, with the increasing amount of data on edge devices, CNNs can hardly complete some tasks in time with limited computing and storage resources. Recently, filter pruning has been regarded as an effective technique to compress and accelerate CNNs, but existing methods rarely prune CNNs from the perspective of compressing high-dimensional tensors. In this article, we propose a novel theory to find redundant information in 3-D tensors, namely, quantified similarity between feature maps (QSFM), and utilize this theory to guide the filter pruning procedure. We perform QSFM on data sets (CIFAR-10, CIFAR-100, and ILSVRC-12) and edge devices and demonstrate that the proposed method can find the redundant information in the neural networks effectively with comparable compression and tolerable drop of accuracy. Without any fine-tuning operation, QSFM can compress ResNet-56 on CIFAR-10 significantly (48.7% FLOPs and 57.9% parameters are reduced) with only a loss of 0.54% in the top-1 accuracy. For the practical application of edge devices, QSFM can accelerate MobileNet-V2 inference speed by 1.53 times with only a loss of 1.23% in the ILSVRC-12 top-1 accuracy. |
| 资助项目 | National Natural Science Foundation of China[62173158] ; National Natural Science Foundation of China[61379134] |
| WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000904931000086 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/51093]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心 |
| 通讯作者 | Wang, Rui |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Beijing 100083, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Zidu,Liu, Xuexin,Huang, Long,et al. QSFM: Model Pruning Based on Quantified Similarity Between Feature Maps for AI on Edge[J]. IEEE INTERNET OF THINGS JOURNAL,2022,9(23):24506-24515. |
| APA | Wang, Zidu.,Liu, Xuexin.,Huang, Long.,Chen, Yunqing.,Zhang, Yufei.,...&Wang, Rui.(2022).QSFM: Model Pruning Based on Quantified Similarity Between Feature Maps for AI on Edge.IEEE INTERNET OF THINGS JOURNAL,9(23),24506-24515. |
| MLA | Wang, Zidu,et al."QSFM: Model Pruning Based on Quantified Similarity Between Feature Maps for AI on Edge".IEEE INTERNET OF THINGS JOURNAL 9.23(2022):24506-24515. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
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。