Optimization of the Bounding Box Regression Process of SSD Model

DOI

10.2991/iccia-19.2019.50How to use a DOI?

Keywords

Intersection over Union (IoU); Generalized IoU (GIoU); SSD; VGG16.

Abstract

Intersection over Union (IoU) has always been the most popular evaluation metric used in object detection benchmarks. However, IoU has a disadvantage that it is not feasible to optimize without overlapping bounding boxes. Therefore, proposed a generalized version as a new loss and a new indicator to address the weakness of IoU. Based on this, this paper innovatively incorporated this Generalized IoU (GIoU) as a loss function into the most advanced SSD object detection network model, and carried out experiments on the original model and the improved model respectively based on the standard detection data set PASCAL VOC. The experimental results proved that the improved model had higher accuracy and better effect.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yuanzhou Yao
AU  - Yuhang Yang
AU  - Xinyue Su
AU  - Yihang Zhao
AU  - Ao Feng
AU  - Yiting Huang
AU  - Haibo Pu
PY  - 2019/07
DA  - 2019/07
TI  - Optimization of the Bounding Box Regression Process of SSD Model
BT  - Proceedings of the 3rd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2019)
PB  - Atlantis Press
SP  - 328
EP  - 336
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccia-19.2019.50
DO  - 10.2991/iccia-19.2019.50
ID  - Yao2019/07
ER  -