CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Learning representative and discriminative image representation by deep appearance and spatial coding
Bingyuan Liu; Jing Liu; Hanqing Lu
Source PublicationComputer Vision and Image Understanding
2015
Volume136Issue:1Pages:23-31
AbstractHow to build a suitable image representation remains a critical problem in computer vision. Traditional Bag-of-Feature (BoF) based models build image representation by the pipeline of local feature extraction, feature coding and spatial pooling. However, three major shortcomings hinder the performance, i.e., the limitation of hand-designed features, the discrimination loss in local appearance coding and the lack of spatial information. To overcome the above limitations, in this paper, we propose a generalized BoF-based framework, which is hierarchically learned by exploring recently developed deep learning methods. First, with raw images as input, we densely extract local patches and learn local features by stacked Independent Subspace Analysis network. The learned features are then transformed to appearance codes by sparse Restricted Boltzmann Machines. Second, we perform spatial max-pooling on a set of over-complete spatial regions, which is generated by covering various spatial distributions, to incorporate more flexible spatial information. Third, a structured sparse Auto-encoder is proposed to explore the region representations into the image-level signature. To learn the proposed hierarchy, we layerwise pre-train the network in unsupervised manner, followed by supervised fine-tuning with image labels. Extensive experiments on different benchmarks, i.e., UIUC-Sports, Caltech-101, Caltech-256, Scene-15 and MIT Indoor-67, demonstrate the effectiveness of our proposed model.
KeywordImage Classification Deep Learning Structured Sparsity
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/13436
Collection模式识别国家重点实验室_图像与视频分析
Corresponding AuthorJing Liu
Recommended Citation
GB/T 7714
Bingyuan Liu,Jing Liu,Hanqing Lu. Learning representative and discriminative image representation by deep appearance and spatial coding[J]. Computer Vision and Image Understanding,2015,136(1):23-31.
APA Bingyuan Liu,Jing Liu,&Hanqing Lu.(2015).Learning representative and discriminative image representation by deep appearance and spatial coding.Computer Vision and Image Understanding,136(1),23-31.
MLA Bingyuan Liu,et al."Learning representative and discriminative image representation by deep appearance and spatial coding".Computer Vision and Image Understanding 136.1(2015):23-31.
Files in This Item: Download All
File Name/Size DocType Version Access License
Learning representat(1491KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Bingyuan Liu]'s Articles
[Jing Liu]'s Articles
[Hanqing Lu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Bingyuan Liu]'s Articles
[Jing Liu]'s Articles
[Hanqing Lu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Bingyuan Liu]'s Articles
[Jing Liu]'s Articles
[Hanqing Lu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Learning representative and discriminative image representation by deep appearance and spatial coding.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

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