TY - GEN
T1 - OBJECT DETECTION IN OPTICAL REMOTE SENSING IMAGES BASED ON POSITIVE SAMPLE REWEIGHTING AND FEATURE DECOUPLING
AU - Yu, Wenqi
AU - Wang, Jiabao
AU - Cheng, Gong
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - The object detection head of Faster R-CNN shared by classification and localization tasks can cause greater harm to training process due to the different features required by the tasks. Besides, Faster R-CNN assigns the same weight to positive proposals, which is unfair to the positive proposal with better regression performance. Aiming at these issues, this paper proposes a novel detection framework, which consists of two important parts, i.e., a Positive Sample Reweighting (PSR) module and a Feature Decoupling (FD) module. Specifically, PSR re-weights each positive proposal according to the positional relationship between each positive proposal and its ground truth. FD employs two parallel branches to extract the weights to decouple features for classification and localization tasks. Experimental results on the DIOR and DOTA datasets show the effectiveness of our proposed method.
AB - The object detection head of Faster R-CNN shared by classification and localization tasks can cause greater harm to training process due to the different features required by the tasks. Besides, Faster R-CNN assigns the same weight to positive proposals, which is unfair to the positive proposal with better regression performance. Aiming at these issues, this paper proposes a novel detection framework, which consists of two important parts, i.e., a Positive Sample Reweighting (PSR) module and a Feature Decoupling (FD) module. Specifically, PSR re-weights each positive proposal according to the positional relationship between each positive proposal and its ground truth. FD employs two parallel branches to extract the weights to decouple features for classification and localization tasks. Experimental results on the DIOR and DOTA datasets show the effectiveness of our proposed method.
KW - Feature decoupling
KW - Object detection
KW - Optical remote sensing images
KW - Sample reweighting
UR - https://www.scopus.com/pages/publications/85129824996
U2 - 10.1109/IGARSS47720.2021.9554236
DO - 10.1109/IGARSS47720.2021.9554236
M3 - 会议稿件
AN - SCOPUS:85129824996
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 4790
EP - 4793
BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Y2 - 12 July 2021 through 16 July 2021
ER -