FSOD4RSI: Few-Shot Object Detection for Remote Sensing Images via Features Aggregation and Scale Attentionopen access
- Authors
- Gao, Honghao; Wu, Shuping; Wang, Ye; Kim, Jung Yoon; Xu, Yueshen
- Issue Date
- Feb-2024
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Remote sensing; Object detection; Feature extraction; Transformers; Training; Adaptation models; Data models; Attention mechanism; feature aggregation; few-shot learning; object detection; remote sensing images
- Citation
- IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, v.17, pp 4784 - 4796
- Pages
- 13
- Journal Title
- IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
- Volume
- 17
- Start Page
- 4784
- End Page
- 4796
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/91592
- DOI
- 10.1109/JSTARS.2024.3362748
- ISSN
- 1939-1404
2151-1535
- Abstract
- Due to the continuous development of few-shot learning, there have been notable advancements in methods for few-shot object detection in recent years. However, most existing methods in this domain primarily focus on natural images, neglecting the challenges posed by variations in object scales, which are usually encountered in remote sensing images. This article proposes a new few-shot object detection model designed to handle the issue of object scale variation in remote sensing images. Our developed model has two essential parts: a feature aggregation module (FAM) and a scale-aware attention module (SAM). Considering the few-shot features of remote sensing images, we designed the FAM to improve the support and query features through channel multiplication operations utilizing a feature pyramid network and a transformer encoder. The created FAM better extracts the global features of remote sensing images and enhances the significant feature representation of few-shot remote sensing objects. In addition, we design the SAM to address the scale variation problems that frequently occur in remote sensing images. By employing multiscale convolutions, the SAM enables the acquisition of contextual features while adapting to objects of varying scales. Extensive experiments were conducted on benchmark datasets, including NWPU VHR-10 and DIOR datasets, and the results show that our model indeed addresses the challenges posed by object scale variation and improves the applicability of few-shot object detection in the remote sensing domain.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/91592)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.