Absolute size IoU loss for the bounding box regression of the object detection

Tian, Di; Yong, Han; Wang, Shu; Chen, Xu; Guan, Tian

doi:10.1016/j.neucom.2022.06.018

Cited by 13 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Methodsmentioning

confidence: 99%

“…By incorporating geometric factors (such as the center distance and aspect ratio) as loss factors, the punishment for training data with higher recognition difficulties is increased, thus reducing the network's robustness. 30 To address this issue, our proposed model introduces the WIoU 31 as the loss function for the detection head. The WIoU is a loss function with a non-monotonic dynamic focusing mechanism.…”

Section: Loss Function Improvementmentioning

confidence: 99%

See 1 more Smart Citation

YOLOvT: CSPNet-based attention for a lightweight textile defect detection model

Hu,

Dai,

et al. 2024

Textile Research Journal

View full text Add to dashboard Cite

Fabric inspection is a crucial process in the textile industry's quality control. Due to the varying structures, textures, geometric features, and spatial distributions of fabric defects, manual fabric inspection is costly and inefficient. Existing fabric defect detection algorithms struggle to strike a balance among efficiency, accuracy, applicability, and deployment costs. In this model, an efficient lightweight fabric defect detection and classification algorithm based on deep convolutional neural networks is proposed. First, the algorithm performs cluster analysis on the fabric defect dataset to ensure that prior boxes better recall objects with fabric defect geometries and spatial characteristics. Next is fusing the convolutional block attention module attention mechanism and Swin Transformer module with the CSPNet structure. This fusion enhances the model's focus on local features and its ability to capture global contextual information without sacrificing the model's inference speed. Moreover, WIoU or Wise-IoU is used as the bounding box loss function of the model, which improves the convergence speed of the bounding box loss and enhances the positioning ability of the model. Finally, the performance of the improved model was validated on a public dataset, showing varying degrees of improvement compared to the baseline model and other state-of-the-art algorithms, meeting the requirements of modern textile processes.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Loss Function Improvementmentioning

confidence: 99%

YOLOvT: CSPNet-based attention for a lightweight textile defect detection model

Hu,

Dai,

et al. 2024

Textile Research Journal

View full text Add to dashboard Cite

show abstract

“…In 2022, Tian et al [23] presented a loss function called AIoU, which improves the accuracy of object recognition. CIoU suffers from penalty term failure in many cases, which causes problems such as insufficient optimization.…”

Section: Intersection Over Unionmentioning

confidence: 99%

Valid-IoU: An Improved IoU-based Loss Function and Its Application to Detection of Defects on Printed Circuit Boards

Vakili

Karimian

Shoaran

et al. 2023

Preprint

View full text Add to dashboard Cite

A crucial component of quality control during printed circuit board (PCB) production is defect detection. The PCB should be inspected during the manufacturing process in order to minimize defects such as printing errors, incorrect component selections, and incorrect soldering. Convolutional neural networks (CNNs) have become widely used due to their high recognition power. One of the factors affecting the accuracy of CNNs is loss function. Intersection over union (IoU) based loss function and its variants such as IoU, generalized IoU (GIoU), distance IoU (DIoU), complete IoU (CIoU), and improved CIoU (ICIoU) are common metrics for bounding box regression. The IoU-based loss functions, such as ICIOU, achieve remarkable success but still have some main drawbacks such as inaccurate regression. The ICIoU performance is degraded under conditions between the ratio of the corresponding height or width of the predicated bounding boxes and the ground truth bounding box. In this paper, an improved IoU called VIoU is introduced to solve this problem. By incorporating VIoU loss into state-of-the-art YOLOv4 object detection algorithm, an average accuracy of 98.63% on the PCB defect detection is achieved which is an improvement compared to existing IoU models.

show abstract

“…Boundary box regression technology has an impact on the accuracy of object detection. D. Tian et al [49] introduced a boundary box regression loss function called absolute size (AIoU) to improve the accuracy of object detection. They discussed the limitations of the previous common loss function in the loss of intersection location, then used the AIoU function, which contains a variety of penalty terms, to improve the regression loss of the boundary box.…”

Section: Loss Functionmentioning

confidence: 99%

ATS-YOLOv7: A Real-Time Multi-Scale Object Detection Method for UAV Aerial Images Based on Improved YOLOv7

Zhang,

Shao,

et al. 2023

Electronics

View full text Add to dashboard Cite

The objects in UAV aerial images have multiple scales, dense distribution, and occlusion, posing considerable challenges for object detection. In order to address this problem, this paper proposes a real-time multi-scale object detection method based on an improved YOLOv7 model (ATS-YOLOv7) for UAV aerial images. First, this paper introduces a feature pyramid network, AF-FPN, which is composed of an adaptive attention module (AAM) and a feature enhancement module (FEM). AF-FPN reduces the loss of deep feature information due to the reduction of feature channels in the convolution process through the AAM and FEM, strengthens the feature perception ability, and improves the detection speed and accuracy for multi-scale objects. Second, we add a prediction head based on a transformer encoder block on the basis of the three-head structure of YOLOv7, improving the ability of the model to capture global information and feature expression, thus achieving efficient detection of objects with tiny scales and dense occlusion. Moreover, as the location loss function of YOLOv7, CIoU (complete intersection over union), cannot facilitate the regression of the prediction box angle to the ground truth box—resulting in a slow convergence rate during model training—this paper proposes a loss function with angle regression, SIoU (soft intersection over union), in order to accelerate the convergence rate during model training. Finally, a series of comparative experiments are carried out on the DIOR dataset. The results indicate that ATS-YOLOv7 has the best detection accuracy (mAP of 87%) and meets the real-time requirements of image processing (detection speed of 94.2 FPS).

show abstract

Absolute size IoU loss for the bounding box regression of the object detection

Cited by 13 publications

References 27 publications

YOLOvT: CSPNet-based attention for a lightweight textile defect detection model

YOLOvT: CSPNet-based attention for a lightweight textile defect detection model

Valid-IoU: An Improved IoU-based Loss Function and Its Application to Detection of Defects on Printed Circuit Boards

ATS-YOLOv7: A Real-Time Multi-Scale Object Detection Method for UAV Aerial Images Based on Improved YOLOv7

Contact Info

Product

Resources

About