CASIA OpenIR  > 脑网络组研究中心
ScaleNet_ a convolutional network to extract multi-scale and fine-grained visual features
Zhang Jinpeng1,2,3,4; Zhang Jinming5; Hu Guyue1,2; Cheng Yang1,2; Yu Shan1,2,3,4
Source PublicationIEEE Access
ISSN2169-3536
2019-10
Issue7Pages:147560-147570
Abstract

Many convolutional neural networks have been proposed for image classification in recent years. Most tend to decrease the plane size of feature maps stage-by-stage, such that the feature maps generated within each stage show the same plane size. This concept governs the design of most classification networks. However, it can also lead to semantic deficiency of high-resolution feature maps as they are always placed in the shallow layers of a network. Here, we propose a novel network architecture, named ScaleNet, which consists of stacked convolution-deconvolution blocks and a multipath residual structure. Unlike most current networks, ScaleNet extracts image features by a cascaded deconstruction-reconstruction process. It can generate scale-variable feature maps within each block and stage, thereby realizing multiscale feature extraction at any depth of the network. Based on the CIFAR-10, CIFAR-100, and ImageNet datasets, ScaleNet demonstrated competitive classification performance compared to state-of-the-art ResNet. In addition, ScaleNet exhibited a powerful ability to capture strong semantic and fine-grained features on its high-resolution feature maps. The code is available at \url{https://github.com/zhjpqq/scalenet}.

KeywordImage Classification Convolutional Neural Networks Resnet Deconvolution
Indexed BySCI
Language英语
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/28345
Collection脑网络组研究中心
Affiliation1.Chinese Acad Sci, Brainnetome Ctr, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
5.Xi An Jiao Tong Univ, State Key Lab Mfg Syst Engn, Xian 710049, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhang Jinpeng,Zhang Jinming,Hu Guyue,et al. ScaleNet_ a convolutional network to extract multi-scale and fine-grained visual features[J]. IEEE Access,2019(7):147560-147570.
APA Zhang Jinpeng,Zhang Jinming,Hu Guyue,Cheng Yang,&Yu Shan.(2019).ScaleNet_ a convolutional network to extract multi-scale and fine-grained visual features.IEEE Access(7),147560-147570.
MLA Zhang Jinpeng,et al."ScaleNet_ a convolutional network to extract multi-scale and fine-grained visual features".IEEE Access .7(2019):147560-147570.
Files in This Item: Download All
File Name/Size DocType Version Access License
ScaleNet_ a convolut(1764KB)期刊 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang Jinpeng]'s Articles
[Zhang Jinming]'s Articles
[Hu Guyue]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang Jinpeng]'s Articles
[Zhang Jinming]'s Articles
[Hu Guyue]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang Jinpeng]'s Articles
[Zhang Jinming]'s Articles
[Hu Guyue]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ScaleNet_ a convolutional network to extract multi-scale and fine-grained visual features.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.