MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning
2023-04-01
Source PublicationSENSORS
ISSN1424-8220
EISSN1424-8220
Volume23Issue:7
Status已发表
DOI10.3390/s23073609
AbstractFew-shot object detection (FSOD) is proposed to solve the application problem of traditional detectors in scenarios lacking training samples. The meta-learning methods have attracted the researchers' attention for their excellent generalization performance. They usually select the same class of support features according to the query labels to weight the query features. However, the model cannot possess the ability of active identification only by using the same category support features, and feature selection causes difficulties in the testing process without labels. The single-scale feature of the model also leads to poor performance in small object detection. In addition, the hard samples in the support branch impact the backbone's representation of the support features, thus impacting the feature weighting process. To overcome these problems, we propose a multi-scale feature fusion and attentive learning (MSFFAL) framework for few-shot object detection. We first design the backbone with multi-scale feature fusion and channel attention mechanism to improve the model's detection accuracy on small objects and the representation of hard support samples. Based on this, we propose an attention loss to replace the feature weighting module. The loss allows the model to consistently represent the objects of the same category in the two branches and realizes the active recognition of the model. The model no longer depends on query labels to select features when testing, optimizing the model testing process. The experiments show that MSFFAL outperforms the state-of-the-art (SOTA) by 0.7-7.8% on the Pascal VOC and exhibits 1.61 times the result of the baseline model in MS COCO's small objects detection.
Keywordfew-shot object detection few-shot learning attention mechanism multi-scale feature fusion
URL查看原文
Indexed BySCI ; EI
Language英语
Funding ProjectSpecial Fund for Basic Research on Scientific Instruments of the National Natural Science Foundation of China[51827814] ; Youth Innovation Promotion Association CAS[2021289]
WOS Research AreaChemistry ; Engineering ; Instruments & Instrumentation
WOS SubjectChemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS IDWOS:000969003700001
PublisherMDPI
EI Accession Number20231613943441
EI KeywordsObject detection
EI Classification Number723.2 Data Processing and Image Processing ; 912.4 Personnel
Original Document TypeJournal article (JA)
Citation statistics
Document Type期刊论文
Identifierhttps://kms.shanghaitech.edu.cn/handle/2MSLDSTB/296030
Collection信息科学与技术学院
信息科学与技术学院_硕士生
Corresponding AuthorZhang, Fuping
Affiliation
1.Chinese Acad Sci, Shanghai Adv Res Inst, Shanghai 201210, Peoples R China
2.Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China
3.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
4.Chinese Acad Sci, Inst Rock & Soil Mech, State Key Lab Geomech & Geotech Engn, Wuhan 430071, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Tianzhao,Sun, Ruoxi,Wan, Yong,et al. MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning[J]. SENSORS,2023,23(7).
APA Zhang, Tianzhao,Sun, Ruoxi,Wan, Yong,Zhang, Fuping,&Wei, Jianming.(2023).MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning.SENSORS,23(7).
MLA Zhang, Tianzhao,et al."MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning".SENSORS 23.7(2023).
Files in This Item: Download All
File Name/Size DocType Version Access License
Related Services
Usage statistics
Scholar Google
Similar articles in Scholar Google
[Zhang, Tianzhao]'s Articles
[Sun, Ruoxi]'s Articles
[Wan, Yong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Tianzhao]'s Articles
[Sun, Ruoxi]'s Articles
[Wan, Yong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Tianzhao]'s Articles
[Sun, Ruoxi]'s Articles
[Wan, Yong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 10.3390@s23073609.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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