IR
Dual Feature Reconstruction Network For Few-shot Image Classification
Guo, Xiaowei; Wu, Jijie; Ren, Kai; Song, Qi; Li, Xiaoxu
2023
会议名称2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
会议录名称2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
页码1579-1584
会议日期October 31, 2023 - November 3, 2023
会议地点Taipei, Taiwan
出版地NEW YORK
出版者Institute of Electrical and Electronics Engineers Inc.
摘要Few-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.
关键词Classification (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
收录类别EI ; CPCI-S
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Computer Science, Theory & Methods
WOS记录号WOS:001108741800247
EI入藏号20235115257000
EI主题词Image classification
EI分类号716.1 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
原始文献类型Conference article (CA)
引用统计
文献类型会议论文
条目标识符https://ir.lut.edu.cn/handle/2XXMBERH/169325
专题兰州理工大学
通讯作者Guo, Xiaowei; Wu, Jijie; Ren, Kai; Song, Qi; Li, Xiaoxu
作者单位Lanzhou University of Technology, Lanzhou, China
第一作者单位兰州理工大学
通讯作者单位兰州理工大学
推荐引用方式
GB/T 7714
Guo, Xiaowei,Wu, Jijie,Ren, Kai,et al. Dual Feature Reconstruction Network For Few-shot Image Classification[C]. NEW YORK:Institute of Electrical and Electronics Engineers Inc.,2023:1579-1584.
条目包含的文件
条目无相关文件。
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Guo, Xiaowei]的文章
[Wu, Jijie]的文章
[Ren, Kai]的文章
百度学术
百度学术中相似的文章
[Guo, Xiaowei]的文章
[Wu, Jijie]的文章
[Ren, Kai]的文章
必应学术
必应学术中相似的文章
[Guo, Xiaowei]的文章
[Wu, Jijie]的文章
[Ren, Kai]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。