Loading [a11y]/accessibility-menu.js
Multi-relational Semantic Distillation for Few-Shot Object Detection | IEEE Conference Publication | IEEE Xplore

Multi-relational Semantic Distillation for Few-Shot Object Detection


Abstract:

While few-shot object detection(FSOD) has been developed to a certain extent, it is still a large margin from practical applications. Most existing methods use traditiona...Show More

Abstract:

While few-shot object detection(FSOD) has been developed to a certain extent, it is still a large margin from practical applications. Most existing methods use traditional object detection methods as the basic framework is improved to a limited extent. Previous methods often ignore the special characterization relationship between support and query images. This paper fully investigates the effect of support images on detection performance and proposes a new FSOD method called Multi-relational Semantic Distillation (MSD). Our approach aims to improve FSOD performance by building a multi-relational semantic representation model with support and query features. In addition, we propose a support enhancement (SE) module based on the self-attention mechanism to enhance the useful information in the support features to mitigate the negative impact of low-quality support images. To verify the effectiveness of MSD, we conduct sufficient experiments on Pascal VOC and MS-COCO datasets. Experiments show that MSD achieves competitive results at low shots compared to other state-of-the-art few-shot detectors.
Date of Conference: 09-12 October 2022
Date Added to IEEE Xplore: 18 November 2022
ISBN Information:

ISSN Information:

Conference Location: Prague, Czech Republic

Funding Agency:


References

References is not available for this document.