ShanghaiTech University Knowledge Management System
MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning | |
2023-04-01 | |
Source Publication | SENSORS
![]() |
ISSN | 1424-8220 |
EISSN | 1424-8220 |
Volume | 23Issue:7 |
Status | 已发表 |
DOI | 10.3390/s23073609 |
Abstract | Few-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. |
Keyword | few-shot object detection few-shot learning attention mechanism multi-scale feature fusion |
URL | 查看原文 |
Indexed By | SCI ; EI |
Language | 英语 |
Funding Project | Special Fund for Basic Research on Scientific Instruments of the National Natural Science Foundation of China[51827814] ; Youth Innovation Promotion Association CAS[2021289] |
WOS Research Area | Chemistry ; Engineering ; Instruments & Instrumentation |
WOS Subject | Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation |
WOS ID | WOS:000969003700001 |
Publisher | MDPI |
EI Accession Number | 20231613943441 |
EI Keywords | Object detection |
EI Classification Number | 723.2 Data Processing and Image Processing ; 912.4 Personnel |
Original Document Type | Journal article (JA) |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | https://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 Author | Zhang, 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 |
Edit Comment
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.