IR
Dual Feature Reconstruction Network For Few-shot Image Classification
Guo, Xiaowei; Wu, Jijie; Ren, Kai; Song, Qi; Li, Xiaoxu
2023
Conference Name2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
Source Publication2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
Pages1579-1584
Conference DateOctober 31, 2023 - November 3, 2023
Conference PlaceTaipei, Taiwan
PublisherInstitute of Electrical and Electronics Engineers Inc.
AbstractFew-shot image classification aims to provide accurate predictions for novelty by learning from a limited number of samples. Classical few-shot image classification methods usually use data augmentation and self-supervision to compensate for the lack of training sample, and introduce migration learning and meta-learning to pre-train the model or accelerate the model optimization, which improves the classification performance of the model. However, with a small amount of labeled sample data, these methods cannot meet the requirements of the model's ability to characterize sample features, resulting in a model that is highly susceptible to overfitting problems. In this paper, we propose a Dual Feature Reconstruction Network (DFRN) for few-shot image classification. The network constructs the double feature vector by two modules, in which the first-level feature module generates an attention mask based on the image to make the feature vector characterize more of the target region, and the secondary feature module interferes with the feature vector to improve its generalization performance. In addition, the network also enhances the classification performance of the model by considering the contextual information of the support classes through an auxiliary loss function. Through extensive experiments, the network proposed in this paper achieves excellent performance on Flowers, CUB and Cars datasets and outperforms other reference fine-grained image classification methods such as FRN. © 2023 IEEE.
KeywordClassification (of information) - Computer vision - Image enhancement - Image reconstruction - Learning systems Accurate prediction - Classification methods - Classification performance - Data augmentation - Feature reconstruction - Features vector - Images classification - Number of samples - Reconstruction networks - Training sample
DOI10.1109/APSIPAASC58517.2023.10317363
Indexed ByEI
Language英语
EI Accession Number20235115257000
EI KeywordsImage classification
EI Classification Number716.1 Information Theory and Signal Processing - 723.2 Data Processing and Image Processing - 723.5 Computer Applications - 741.2 Vision - 903.1 Information Sources and Analysis
Original literature typeConference article (CA)
Citation statistics
none
Document Type会议论文
Identifierhttps://ir.lut.edu.cn/handle/2XXMBERH/169325
Collection兰州理工大学
Corresponding AuthorGuo, Xiaowei; Wu, Jijie; Ren, Kai; Song, Qi; Li, Xiaoxu
AffiliationLanzhou University of Technology, Lanzhou, China
First Author AffilicationLanzhou University of Technology
Corresponding Author AffilicationLanzhou University of Technology
Recommended Citation
GB/T 7714
Guo, Xiaowei,Wu, Jijie,Ren, Kai,et al. Dual Feature Reconstruction Network For Few-shot Image Classification[C]:Institute of Electrical and Electronics Engineers Inc.,2023:1579-1584.
Files in This Item:
There are no files associated with this item.
Related Services
Usage statistics
Google Scholar
Similar articles in Google Scholar
[Guo, Xiaowei]'s Articles
[Wu, Jijie]'s Articles
[Ren, Kai]'s Articles
Baidu academic
Similar articles in Baidu academic
[Guo, Xiaowei]'s Articles
[Wu, Jijie]'s Articles
[Ren, Kai]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Guo, Xiaowei]'s Articles
[Wu, Jijie]'s Articles
[Ren, Kai]'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.