Dual Feature Reconstruction Network For Few-shot Image Classification

doi:10.1109/APSIPAASC58517.2023.10317363

	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
DOI	10.1109/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	无
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.