TY - GEN
T1 - SINGLE-SHOT BALANCED DETECTOR FOR GEOSPATIAL OBJECT DETECTION
AU - Liu, Yanfeng
AU - Li, Qiang
AU - Yuan, Yuan
AU - Wang, Qi
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - Geospatial object detection is an essential task in remote sensing community. One-stage methods based on deep learning have faster running speed but cannot reach higher detection accuracy than two-stage methods. In this paper, to achieve excellent speed/accuracy trade-off for geospatial object detection, a single-shot balanced detector is presented. First, a balanced feature pyramid network (BFPN) is designed, which can balance semantic information and spatial information between high-level and shallow-level features adaptively. Second, we propose a task-interactive head (TIH). It can reduce the task misalignment between classification and regression. Extensive experiments show that the improved detector obtains significant detection accuracy with considerable speed on two benchmark datasets.
AB - Geospatial object detection is an essential task in remote sensing community. One-stage methods based on deep learning have faster running speed but cannot reach higher detection accuracy than two-stage methods. In this paper, to achieve excellent speed/accuracy trade-off for geospatial object detection, a single-shot balanced detector is presented. First, a balanced feature pyramid network (BFPN) is designed, which can balance semantic information and spatial information between high-level and shallow-level features adaptively. Second, we propose a task-interactive head (TIH). It can reduce the task misalignment between classification and regression. Extensive experiments show that the improved detector obtains significant detection accuracy with considerable speed on two benchmark datasets.
KW - Geospatial object detection
KW - multi-scale balance learning
KW - one-stage detector
KW - task-interactive head
UR - http://www.scopus.com/inward/record.url?scp=85131236408&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9746853
DO - 10.1109/ICASSP43922.2022.9746853
M3 - 会议稿件
AN - SCOPUS:85131236408
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 2529
EP - 2533
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Y2 - 22 May 2022 through 27 May 2022
ER -