TY - GEN
T1 - You Get What You Focus on
T2 - 2021 International Joint Conference on Neural Networks, IJCNN 2021
AU - Gu, Xinyu
AU - Gao, Chao
AU - Lu, Zheng
AU - Cui, Tianxiang
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/7/18
Y1 - 2021/7/18
N2 - Loss functions are essential to bounding box regression which plays a significant role in deep learning based object detection. Despite the effectiveness of the popular Intersection over Union (IoU) based losses, there is still an imbalance problem of high- and low-quality predicted bounding boxes, impeding the accuracy and convergence speed during bound box regression. Specifically, we observe that the huge amount of predicted bounding boxes having small overlapping regions with ground truth box overwhelms the amount of predicted bounding boxes having large overlapping regions. In this paper, we propose a simple weighting factor that is able to reshape the existing IoU-based losses according to a geometric relationship of bounding boxes. In this way, we are able to effectively down-weight the contribution of low-quality predicted boxes and focus training on high-quality ones. Extensive experiments have been carried out on popular IoU-based losses with various object detection techniques. By simply incorporating the proposed weighting factor, we are able to achieve notable performance gains on the popular MS COCO dataset.
AB - Loss functions are essential to bounding box regression which plays a significant role in deep learning based object detection. Despite the effectiveness of the popular Intersection over Union (IoU) based losses, there is still an imbalance problem of high- and low-quality predicted bounding boxes, impeding the accuracy and convergence speed during bound box regression. Specifically, we observe that the huge amount of predicted bounding boxes having small overlapping regions with ground truth box overwhelms the amount of predicted bounding boxes having large overlapping regions. In this paper, we propose a simple weighting factor that is able to reshape the existing IoU-based losses according to a geometric relationship of bounding boxes. In this way, we are able to effectively down-weight the contribution of low-quality predicted boxes and focus training on high-quality ones. Extensive experiments have been carried out on popular IoU-based losses with various object detection techniques. By simply incorporating the proposed weighting factor, we are able to achieve notable performance gains on the popular MS COCO dataset.
KW - IoU loss
KW - bounding box regression
KW - object detection
UR - http://www.scopus.com/inward/record.url?scp=85116486224&partnerID=8YFLogxK
U2 - 10.1109/IJCNN52387.2021.9534463
DO - 10.1109/IJCNN52387.2021.9534463
M3 - Conference contribution
AN - SCOPUS:85116486224
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - IJCNN 2021 - International Joint Conference on Neural Networks, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 18 July 2021 through 22 July 2021
ER -