Back to Search Start Over

Dual-Awareness Attention for Few-Shot Object Detection

Authors :
Chen, Tung-I
Liu, Yueh-Cheng
Su, Hung-Ting
Chang, Yu-Cheng
Lin, Yu-Hsiang
Yeh, Jia-Fong
Chen, Wen-Chin
Hsu, Winston H.
Source :
IEEE Transactions on Multimedia 2021
Publication Year :
2021

Abstract

While recent progress has significantly boosted few-shot classification (FSC) performance, few-shot object detection (FSOD) remains challenging for modern learning systems. Existing FSOD systems follow FSC approaches, ignoring critical issues such as spatial variability and uncertain representations, and consequently result in low performance. Observing this, we propose a novel \textbf{Dual-Awareness Attention (DAnA)} mechanism that enables networks to adaptively interpret the given support images. DAnA transforms support images into \textbf{query-position-aware} (QPA) features, guiding detection networks precisely by assigning customized support information to each local region of the query. In addition, the proposed DAnA component is flexible and adaptable to multiple existing object detection frameworks. By adopting DAnA, conventional object detection networks, Faster R-CNN and RetinaNet, which are not designed explicitly for few-shot learning, reach state-of-the-art performance in FSOD tasks. In comparison with previous methods, our model significantly increases the performance by 47\% (+6.9 AP), showing remarkable ability under various evaluation settings.

Details

Database :
arXiv
Journal :
IEEE Transactions on Multimedia 2021
Publication Type :
Report
Accession number :
edsarx.2102.12152
Document Type :
Working Paper