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

Abstract

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.

Enhanced YOLOv5: An Efficient Road Object Detection Method

“…Specifically, the operation of the CBAM [36] module is as follows: First, the cha attention module performs average pooling and max pooling on the entire input fe map to extract feature information. Then, this feature information is passed through fully connected layers for processing and a sigmoid function is applied to gener channel attention weight in the range of 0 to 1.…”

“…In traditional NMS algorithms, a fixed IoU [36] threshold is set as the suppression threshold, as shown in Figure 14. All detection boxes are sorted by confidence, and all detection boxes are traversed from high to low confidence one by one.…”

STAE‐YOLO: Intelligent detection algorithm for risk management of construction machinery intrusion on transmission lines based on visual perception

“…For the target detection task, the loss function of the bounding box regression (BBR) [34] is crucial. The baseline model we use is the complete-intersection over union (CIoU) loss [35], which considers three geometric measures, including the overlap between the predicted and target frames, the distance to the centroid, and the consistency of the aspect ratio.…”

DYNet: A Printed Book Detection Model Using Dual Kernel Neural Networks

“…The other part is IoU [ 22 ] loss ; IoU is Intersection over Union (IoU), as shown in the following equation and Figure 7 ; is the Intersection over Union of two targets recognized by STSM; is the Intersection over Union of two targets recognized by STSM. …”