CASIA OpenIR
Deep sparse representation-based mid-level visual elements discovery in fine-grained classification
Lv, Le; Zhao, Dongbin; Shao, Kun
Source PublicationSOFT COMPUTING
ISSN1432-7643
2019-09-01
Volume23Issue:18Pages:8711-8722
Corresponding AuthorZhao, Dongbin(dongbin.zhao@ia.ac.cn)
AbstractIn this paper, we propose a new mid-level visual elements discovery method and apply it to the fine-grained classification. We present the duality between image patches and features extracted by the convolutional winner-take-all autoencoder (CONV-WTA-AE). The sparsity constraints used by CONV-WTA-AE make a group of objects sharing the same feature components. Hence, the image patches could be clustered by their sharing feature components and the feature components can be clustered by their co-occurrence in the image patches. We propose formulating the mid-level visual elements mining as a bipartite graph partitioning problem. The spectral partitioning algorithm is employed to co-cluster image patches and feature components. The CONV-WTA-AE is an unsupervised feature learning method. Hence, it avoids using expensive annotations. Our experiments demonstrate that the spectral partitioning method is very efficient but only the confident instances in a cluster are well discriminated. The similarity metric used by this algorithm is not accurate enough. Hence, we propose training a group of linear support vector machine (SVM) to refine the clustering results. These SVMs will be trained on the initial confident instances and provide a better discriminative similarity. Then we can re-assign instances to each clusters. To avoid overfitting, this process is iterated on many data subsets. We conduct a series of experiments on the MNIST dataset to verify our algorithm. The experimental results show that our method can discover meaningful image patch clusters. In the fine-grained classification task, visual elements are input into an ensemble of convolutional neural networks. The experiments on the CompCars dataset illustrate that our method can achieve the state-of-the-art performance.
KeywordMid-level visual elements discovery Fine-grained classification Winner-take-all autoencoder Bipartite graph spectral partitioning
DOI10.1007/s00500-018-3468-3
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China (NSFC)[61273136] ; National Natural Science Foundation of China (NSFC)[61573353] ; National Natural Science Foundation of China (NSFC)[61533017]
Funding OrganizationNational Natural Science Foundation of China (NSFC)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications
WOS IDWOS:000478897000031
PublisherSPRINGER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/27554
Collection中国科学院自动化研究所
Corresponding AuthorZhao, Dongbin
AffiliationChinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Lv, Le,Zhao, Dongbin,Shao, Kun. Deep sparse representation-based mid-level visual elements discovery in fine-grained classification[J]. SOFT COMPUTING,2019,23(18):8711-8722.
APA Lv, Le,Zhao, Dongbin,&Shao, Kun.(2019).Deep sparse representation-based mid-level visual elements discovery in fine-grained classification.SOFT COMPUTING,23(18),8711-8722.
MLA Lv, Le,et al."Deep sparse representation-based mid-level visual elements discovery in fine-grained classification".SOFT COMPUTING 23.18(2019):8711-8722.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Lv, Le]'s Articles
[Zhao, Dongbin]'s Articles
[Shao, Kun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lv, Le]'s Articles
[Zhao, Dongbin]'s Articles
[Shao, Kun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lv, Le]'s Articles
[Zhao, Dongbin]'s Articles
[Shao, Kun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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