Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression

Bounding box regression is a crucial step in object detection, directly affecting the localization performance of the detected objects. Especially in small object detection, an excellent bounding box regression loss can significantly alleviate the problem of missing small objects. However, there are...

Full description

Bibliographic Details
Main Authors: Delong Cai, Zhaoyun Zhang, Zhi Zhang
Format: Article
Language:English
Published: MDPI AG 2023-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/23/10/4961
_version_ 1797598272671449088
author Delong Cai
Zhaoyun Zhang
Zhi Zhang
author_facet Delong Cai
Zhaoyun Zhang
Zhi Zhang
author_sort Delong Cai
collection DOAJ
description Bounding box regression is a crucial step in object detection, directly affecting the localization performance of the detected objects. Especially in small object detection, an excellent bounding box regression loss can significantly alleviate the problem of missing small objects. However, there are two major problems with the broad Intersection over Union (IoU) losses, also known as Broad IoU losses (BIoU losses) in bounding box regression: (i) BIoU losses cannot provide more effective fitting information for predicted boxes as they approach the target box, resulting in slow convergence and inaccurate regression results; (ii) most localization loss functions do not fully utilize the spatial information of the target, namely the target’s foreground area, during the fitting process. Therefore, this paper proposes the Corner-point and Foreground-area IoU loss (CFIoU loss) function by delving into the potential for bounding box regression losses to overcome these issues. First, we use the normalized corner point distance between the two boxes instead of the normalized center-point distance used in the BIoU losses, which effectively suppresses the problem of BIoU losses degrading to IoU loss when the two boxes are close. Second, we add adaptive target information to the loss function to provide richer target information to optimize the bounding box regression process, especially for small object detection. Finally, we conducted simulation experiments on bounding box regression to validate our hypothesis. At the same time, we conducted quantitative comparisons of the current mainstream BIoU losses and our proposed CFIoU loss on the small object public datasets VisDrone2019 and SODA-D using the latest anchor-based YOLOv5 and anchor-free YOLOv8 object detection algorithms. The experimental results demonstrate that YOLOv5s (+3.12% Recall, +2.73% mAP@0.5, and +1.91% mAP@0.5:0.95) and YOLOv8s (+1.72% Recall and +0.60% mAP@0.5), both incorporating the CFIoU loss, achieved the highest performance improvement on the VisDrone2019 test set. Similarly, YOLOv5s (+6% Recall, +13.08% mAP@0.5, and +14.29% mAP@0.5:0.95) and YOLOv8s (+3.36% Recall, +3.66% mAP@0.5, and +4.05% mAP@0.5:0.95), both incorporating the CFIoU loss, also achieved the highest performance improvement on the SODA-D test set. These results indicate the effectiveness and superiority of the CFIoU loss in small object detection. Additionally, we conducted comparative experiments by fusing the CFIoU loss and the BIoU loss with the SSD algorithm, which is not proficient in small object detection. The experimental results demonstrate that the SSD algorithm incorporating the CFIoU loss achieved the highest improvement in the AP (+5.59%) and AP75 (+5.37%) metrics, indicating that the CFIoU loss can also improve the performance of algorithms that are not proficient in small object detection.
first_indexed 2024-03-11T03:20:02Z
format Article
id doaj.art-0606b87a1ad643c483a2bca3e64faf45
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-11T03:20:02Z
publishDate 2023-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-0606b87a1ad643c483a2bca3e64faf452023-11-18T03:15:15ZengMDPI AGSensors1424-82202023-05-012310496110.3390/s23104961Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box RegressionDelong Cai0Zhaoyun Zhang1Zhi Zhang2School of Electrical Engineering and Intelligentization, DongGuan University of Technology, Dongguan 523000, ChinaSchool of Electrical Engineering and Intelligentization, DongGuan University of Technology, Dongguan 523000, ChinaSchool of Electrical Engineering and Intelligentization, DongGuan University of Technology, Dongguan 523000, ChinaBounding box regression is a crucial step in object detection, directly affecting the localization performance of the detected objects. Especially in small object detection, an excellent bounding box regression loss can significantly alleviate the problem of missing small objects. However, there are two major problems with the broad Intersection over Union (IoU) losses, also known as Broad IoU losses (BIoU losses) in bounding box regression: (i) BIoU losses cannot provide more effective fitting information for predicted boxes as they approach the target box, resulting in slow convergence and inaccurate regression results; (ii) most localization loss functions do not fully utilize the spatial information of the target, namely the target’s foreground area, during the fitting process. Therefore, this paper proposes the Corner-point and Foreground-area IoU loss (CFIoU loss) function by delving into the potential for bounding box regression losses to overcome these issues. First, we use the normalized corner point distance between the two boxes instead of the normalized center-point distance used in the BIoU losses, which effectively suppresses the problem of BIoU losses degrading to IoU loss when the two boxes are close. Second, we add adaptive target information to the loss function to provide richer target information to optimize the bounding box regression process, especially for small object detection. Finally, we conducted simulation experiments on bounding box regression to validate our hypothesis. At the same time, we conducted quantitative comparisons of the current mainstream BIoU losses and our proposed CFIoU loss on the small object public datasets VisDrone2019 and SODA-D using the latest anchor-based YOLOv5 and anchor-free YOLOv8 object detection algorithms. The experimental results demonstrate that YOLOv5s (+3.12% Recall, +2.73% mAP@0.5, and +1.91% mAP@0.5:0.95) and YOLOv8s (+1.72% Recall and +0.60% mAP@0.5), both incorporating the CFIoU loss, achieved the highest performance improvement on the VisDrone2019 test set. Similarly, YOLOv5s (+6% Recall, +13.08% mAP@0.5, and +14.29% mAP@0.5:0.95) and YOLOv8s (+3.36% Recall, +3.66% mAP@0.5, and +4.05% mAP@0.5:0.95), both incorporating the CFIoU loss, also achieved the highest performance improvement on the SODA-D test set. These results indicate the effectiveness and superiority of the CFIoU loss in small object detection. Additionally, we conducted comparative experiments by fusing the CFIoU loss and the BIoU loss with the SSD algorithm, which is not proficient in small object detection. The experimental results demonstrate that the SSD algorithm incorporating the CFIoU loss achieved the highest improvement in the AP (+5.59%) and AP75 (+5.37%) metrics, indicating that the CFIoU loss can also improve the performance of algorithms that are not proficient in small object detection.https://www.mdpi.com/1424-8220/23/10/4961object detectionloss functionsmall objectbounding box regression
spellingShingle Delong Cai
Zhaoyun Zhang
Zhi Zhang
Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression
Sensors
object detection
loss function
small object
bounding box regression
title Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression
title_full Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression
title_fullStr Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression
title_full_unstemmed Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression
title_short Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression
title_sort corner point and foreground area iou loss better localization of small objects in bounding box regression
topic object detection
loss function
small object
bounding box regression
url https://www.mdpi.com/1424-8220/23/10/4961
work_keys_str_mv AT delongcai cornerpointandforegroundareaioulossbetterlocalizationofsmallobjectsinboundingboxregression
AT zhaoyunzhang cornerpointandforegroundareaioulossbetterlocalizationofsmallobjectsinboundingboxregression
AT zhizhang cornerpointandforegroundareaioulossbetterlocalizationofsmallobjectsinboundingboxregression