中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Local-binarized very deep residual network for visual categorization

文献类型：期刊论文

作者Liu, Xuejing1,2; Li, Liang1; Wang, Shuhui1; Zha, Zheng-Jun3; Huang, Qingming1,2
刊名NEUROCOMPUTING
出版日期2021-03-21
卷号430页码:82-93
关键词Network compression and acceleration Pose estimation Object recognition Saliency detection Local binary residual block
ISSN号0925-2312
DOI10.1016/j.neucom.2020.11.041
英文摘要Residual networks usually require more layers to achieve remarkable performance in complex visual categorization tasks, such as pose estimation. However, the increasing number of layers leads to a heavy burden on training and forward inference as well as over-fitting. This paper proposed local binary residual block (LBB) to promote the very deep residual networks on the trainable parameters, FLOPs and accuracy. In each LBB, the 3 x 3 filters are binarized based on Bernoulli distribution under a sparse constraint, an activation function is prepared to trigger the non-linear response, and the linear 1 x 1 filters are learned in a real-valued way. After stochastic binarized initialization, the 3 x 3 filters in LBB need not be updated during training. The above architecture reduces at least 69.2% trainable parameters and 70.5% FLOPs compared to the original model. The LBB is derived from three observations: 1) Activated responses of one standard k x k convolutional layer can be approximated by combining binarized k x k filters with 1 x 1 filters; 2) Most computation in the very deep residual networks is spent on the 3 x 3 convolutions; and 3) 1 x 1 filters play an important role in cross-channel information integration. In addition, the LBB module is suitable for the very deep network framework, including stacked hourglass network and pyramid residual modules. Experiments are conducted on MPII and LSP dataset for pose estimation task; CIFAR-10, CIFAR-100 and ImageNet datasets for object recognition; ECSSD, HKU-IS, PASCAL-S, DUT-OMRON, DUTS for saliency detection. The results show that our model can accelerate the training and inference of the network with only a slight performance degradation. (c) 2020 Elsevier B.V. All rights reserved.
资助项目National Key R&D Program of China[2018YFE0303104] ; National Natural Science Foundation of China[61732007] ; National Natural Science Foundation of China[61771457]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000617365300008
出版者ELSEVIER
源URL[http://119.78.100.204/handle/2XEOYT63/16230]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Li, Liang
作者单位1.Chinese Acad Sci, Inst Comp Technol, CAS, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100190, Peoples R China
3.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230027, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Xuejing,Li, Liang,Wang, Shuhui,et al. Local-binarized very deep residual network for visual categorization[J]. NEUROCOMPUTING,2021,430:82-93.
APA Liu, Xuejing,Li, Liang,Wang, Shuhui,Zha, Zheng-Jun,&Huang, Qingming.(2021).Local-binarized very deep residual network for visual categorization.NEUROCOMPUTING,430,82-93.
MLA Liu, Xuejing,et al."Local-binarized very deep residual network for visual categorization".NEUROCOMPUTING 430(2021):82-93.

入库方式： OAI收割

来源：计算技术研究所

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。