A Novel One-Shot Object Detection via Multifeature Auxiliary Information

With the advantage of using only a limited number of samples, few-shot learning has been developed rapidly in recent years. It is mostly applied in the object classification or detection of a small number of samples which is typically less than ten. However, there is not much research related to few...

Full description

Saved in:
Bibliographic Details
Published in:Security and communication networks 2022-02, Vol.2022, p.1-9
Main Authors: Song, Yu, Li, Min, Du, Weidong, Gou, Yao, Wu, Zhaoqing, He, Yujie
Format: Article
Language:English
Subjects:
Algorithms
Classification
Datasets
Feature extraction
Modules
Neural networks
Object recognition
Semantics
Teaching methods
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the advantage of using only a limited number of samples, few-shot learning has been developed rapidly in recent years. It is mostly applied in the object classification or detection of a small number of samples which is typically less than ten. However, there is not much research related to few-shot detection, especially one-shot detection. In this paper, the multifeature information-assisted one-shot detection method is proposed to improve the accuracy of one-shot object detection. Specifically, two auxiliary modules are applied to the detection algorithm: Semantic Feature Module (SFM) and Detail Feature Module (DFM), which, respectively, extract semantic feature information and detailed feature information of samples in the support set. Then these two kinds of information are then calculated with the feature image extracted from the query image to obtain the corresponding auxiliary information that is used to complete one-shot detection. Thanks to the two auxiliary modules, which can retain more semantic and detailed information of samples in the support set, the proposed method can enhance the utilization rate of sample feature information and improve object detection accuracy by 2.97% compared to the benchmark method.
ISSN:1939-0114
1939-0122
DOI:10.1155/2022/6805526