https://scholars.lib.ntu.edu.tw/handle/123456789/607484
標題: | Dual-Awareness Attention for Few-Shot Object Detection | 作者: | Chen T Liu Y Su H Chang Y Lin Y Yeh J WEN-CHIN CHEN WINSTON HSU |
關鍵字: | Adaptation models;Correlation;Deep learning;Detectors;Feature extraction;few-shot object detection;object detection;Object detection;Power capacitors;Task analysis;visual attention | 公開日期: | 2021 | 來源出版物: | IEEE Transactions on Multimedia | 摘要: | 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 Dual-Awareness Attention (DAnA) mechanism that enables networks to adaptively interpret the given support images. DAnA transforms support images into 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. IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118619086&doi=10.1109%2fTMM.2021.3125195&partnerID=40&md5=49afb5870428706286bba367ca4ec612 https://scholars.lib.ntu.edu.tw/handle/123456789/607484 |
ISSN: | 15209210 | DOI: | 10.1109/TMM.2021.3125195 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。