TY - GEN
T1 - PIoU Loss
T2 - 16th European Conference on Computer Vision 2020
AU - Chen, Zhiming
AU - Chen, Kean
AU - Lin, Weiyao
AU - See, John
AU - Yu, Hui
AU - Ke, Yan
AU - Yang, Cong
N1 - Funding Information:
Acknowledgements. The paper is supported in part by the following grants: China Major Project for New Generation of AI Grant (No. 2018AAA0100400), National Natural Science Foundation of China (No. 61971277). The work is also supported by funding from Clobotics under the Joint Research Program of Smart Retail.
Publisher Copyright:
© 2020, Springer Nature Switzerland AG.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/10/29
Y1 - 2020/10/29
N2 - Object detection using an oriented bounding box (OBB) can better target rotated objects by reducing the overlap with background areas. Existing OBB approaches are mostly built on horizontal bounding box detectors by introducing an additional angle dimension optimized by a distance loss. However, as the distance loss only minimizes the angle error of the OBB and that it loosely correlates to the IoU, it is insensitive to objects with high aspect ratios. Therefore, a novel loss, Pixels-IoU (PIoU) Loss, is formulated to exploit both the angle and IoU for accurate OBB regression. The PIoU loss is derived from IoU metric with a pixel-wise form, which is simple and suitable for both horizontal and oriented bounding box. To demonstrate its effectiveness, we evaluate the PIoU loss on both anchor-based and anchor-free frameworks. The experimental results show that PIoU loss can dramatically improve the performance of OBB detectors, particularly on objects with high aspect ratios and complex backgrounds. Besides, previous evaluation datasets did not include scenarios where the objects have high aspect ratios, hence a new dataset, Retail50K, is introduced to encourage the community to adapt OBB detectors for more complex environments.
AB - Object detection using an oriented bounding box (OBB) can better target rotated objects by reducing the overlap with background areas. Existing OBB approaches are mostly built on horizontal bounding box detectors by introducing an additional angle dimension optimized by a distance loss. However, as the distance loss only minimizes the angle error of the OBB and that it loosely correlates to the IoU, it is insensitive to objects with high aspect ratios. Therefore, a novel loss, Pixels-IoU (PIoU) Loss, is formulated to exploit both the angle and IoU for accurate OBB regression. The PIoU loss is derived from IoU metric with a pixel-wise form, which is simple and suitable for both horizontal and oriented bounding box. To demonstrate its effectiveness, we evaluate the PIoU loss on both anchor-based and anchor-free frameworks. The experimental results show that PIoU loss can dramatically improve the performance of OBB detectors, particularly on objects with high aspect ratios and complex backgrounds. Besides, previous evaluation datasets did not include scenarios where the objects have high aspect ratios, hence a new dataset, Retail50K, is introduced to encourage the community to adapt OBB detectors for more complex environments.
KW - IoU loss
KW - Orientated object detection
UR - http://www.scopus.com/inward/record.url?scp=85097394624&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-58558-7_12
DO - 10.1007/978-3-030-58558-7_12
M3 - Conference contribution
AN - SCOPUS:85097394624
SN - 9783030585570
T3 - Lecture Notes in Computer Science
SP - 195
EP - 211
BT - Computer Vision. ECCV 2020
A2 - Vedaldi, Andrea
A2 - Bischof, Horst
A2 - Brox, Thomas
A2 - Frahm, Jan-Michael
PB - Springer
Y2 - 23 August 2020 through 28 August 2020
ER -