LCornerIoU: An Improved IoU-based Loss Function for Accurate Bounding Box Regression

The regression loss function is a key factor in the training and optimization process of object detection. The current mainstream regression loss functions are Ln norm loss, IOU loss and CIOU loss. This paper proposes the Scale-Sensitive IOU(SIOU) loss, a new loss function different from the above all, which could solve the issues that the current loss functions cannot distinguish the two bounding boxes in some special cases when the target area scales in one image vary greatly during training process, thereby leading to the improper regression loss calculation and the slowing down of the optimization. An area scale regulating factor Y is added on the basis of CIOU loss to adjust the loss values of the bounding boxes, which could distinguish all the boxes quantitatively in theory thus gets a faster converging speed and better optimization. Through analysis and simulation comparison among the several loss functions, the superiority of SIOU loss is verified. Furthermore, by incorporating SIOU loss into YOLO v4, Faster R-CNN and SSD on the two mainstream aerial remote sensing datasets, i.e., DIOR and NWPU VHR-10, the detection precisions improve by 10.2% than IOU loss and 2.8% than CIOU loss respectively.

Loss functions, such as the IoU Loss function and the GIoU (Generalized Intersection over Union) Loss function have been put forward to replace regression loss functions commonly used in regression loss calculation. GIoU Loss alleviates the vanishing gradient in the case of the non-overlapping, but it will completely degenerate into the IoU Loss function when bounding boxes overlap totally, which fails to achieve the optimization effect. To solve this problem, some improvements are proposed in this paper on the basis of the GIoU Loss function, taking into account the overlap rate of complete overlap of bounding boxes. In PASCAL VOC data, the experimental results demonstrate that the AP of NGIoU Loss function in the YOLOv4 model is 47.68%, 1.15% higher than that of the GIoU Loss function, and the highest map value is 86.79% in the YOLOv5 model.

The fast advancement of unmanned aerial vehicle (UAV) technology has facilitated its use across a wide range of scenarios. Due to the high mobility and flexibility of drones, the images they capture often exhibit significant scale variations and severe object occlusions, leading to a high density of small objects. However, the existing object detection algorithms struggle with detecting small objects effectively in cross-scale detection scenarios. To overcome these difficulties, we introduce a new object detection model, RPS-YOLO, based on the YOLOv8 architecture. Unlike the existing methods that rely on traditional feature pyramids, our approach introduces a recursive feature pyramid (RFP) structure. This structure performs two rounds of feature extraction, and we reduce one downsampling step in the first round to enhance attention to small objects during cross-scale detection. Additionally, we design a novel attention mechanism that improves feature representation and mitigates feature degradation during convolution by capturing spatial- and channel-specific details. Another key innovation is the proposed Localization IOU (LIOU) loss function for bounding box regression, which accelerates the regression process by incorporating angular constraints. Experiments conducted on the VisDrone-DET2021 and UAVDT datasets show that RPS-YOLO surpasses YOLOv8s, with an mAP50 improvement of 8.2% and 3.4%, respectively. Our approach demonstrates that incorporating recursive feature extraction and exploiting detailed information for multi-scale detection significantly improves detection performance, particularly for small objects in UAV images.

Advanced Siamese visual object tracking architectures are jointly trained using pair-wise input images to perform target classification and bounding box regression. They have achieved promising results in recent benchmarks and competitions. However, the existing methods suffer from two limitations: First, though the Siamese structure can estimate the target state in an instance frame, provided the target appearance does not deviate too much from the template, the detection of the target in an image cannot be guaranteed in the presence of severe appearance variations. Second, despite the classification and regression tasks sharing the same output from the backbone network, their specific modules and loss functions are invariably designed independently, without promoting any interaction. Yet, in a general tracking task, the centre classification and bounding box regression tasks are collaboratively working to estimate the final target location. To address the above issues, it is essential to perform target-agnostic detection so as to promote cross-task interactions in a Siamese-based tracking framework. In this work, we endow a novel network with a target-agnostic object detection module to complement the direct target inference, and to avoid or minimise the misalignment of the key cues of potential template-instance matches. To unify the multi-task learning formulation, we develop a cross-task interaction module to ensure consistent supervision of the classification and regression branches, improving the synergy of different branches. To eliminate potential inconsistencies that may arise within a multi-task architecture, we assign adaptive labels, rather than fixed hard labels, to supervise the network training more effectively. The experimental results obtained on several benchmarks, i.e., OTB100, UAV123, VOT2018, VOT2019, and LaSOT, demonstrate the effectiveness of the advanced target detection module, as well as the cross-task interaction, exhibiting superior tracking performance as compared with the state-of-the-art tracking methods.

Estimation of traffic flow parameters based on computer vision is still a very popular challenge. In particular, the detection problems such as occlusion, small targets, luminance variations, and lighting jitter, etc., are caused by dense traffic scenes and complex weather conditions. Previous studies about detecting and tracking methods focused on daytime and nighttime or single weather condition, but the performance of this model will decline dramatically due to complex conditions. In this paper, a framework for estimating traffic flow parameters in complex environments is presented, in which Ghost-YOLOv8 vehicle detection model is proposed. GhostConv is used to replace part of Conv and a new C2fGhost module is designed to replace part of C2f, reducing the number of parameters and improving the detection performance of the model; The global attention mechanism module is added to the neck network, which strengthens the semantic and location information in the features and improves the model’s ability of feature fusion; In view of the loss of semantic information caused by different scales in detecting small targets, a small target detection layer is added to enhance a combination of deep and shallow semantic information; The GIoU bounding loss function is used instead of the original loss function, which improves the performance of the network’s bounding box regression. Then, combining DeepSORT tracking algorithm and virtual line counting method, the proposed framework estimates traffic flow parameters, including volume, speed, and density in complex environments. The experimental results show that compared with the original model in the UA-DETRAC dataset, the improved YOLOv8 model’s the accuracy is increased by 1.4%, and the parameter number and model size are reduced by 0.229G and 0.2MB respectively. In addition, the framework has good robustness, reaching 97.56% accuracy when estimating average traffic flow parameters. It is sufficient to overcome complex weather conditions and effectively help control traffic for intelligent transportation systems and traffic management to provide good data support. In conclusion, it shows that the model can reduce the number and size of model parameters and improve the detection precision as well as meeting the requirements of edge computing devices and having better real-time performance, so it has practical application value.

Robust regularized extreme learning machine for regression using iteratively reweighted least squares

Gaussian-IoU loss: Better learning for bounding box regression on PCB component detection

An object detector based on convolutional neural network (CNN) has been widely used in the field of computer vision because of its simplicity and efficiency. The average accuracy of CNN model detection results in the object detector is greatly affected by the loss function. The precision of the localization algorithm in the loss function is the main factor affecting the result. Based on the complete intersection over union (CIoU) loss function, an improved penalty function is proposed to improve the localization accuracy. Specifically, the algorithm more comprehensively considers matching bounding boxes between prediction with ground truth, using the proportional relationship of the aspect ratio from both bounding boxes. Under the same aspect ratio of the two bounding boxes, the influence factors of the prediction box on localization accuracy were considered. In this way, the function of the penalty function is strengthened, and localization accuracy of the network model improved. This loss function is called Improved CIoU (ICIoU). Experiments on the Udacity, PASCAL VOC, and MS COCO datasets have demonstrated the effectiveness of ICIoU in improving localization accuracy of network models by using the one-stage object detector YOLOv4. Compared with CIoU, the proposed ICIoU improved average precision (AP) by 0.57% and AP75 by 0.12% on Udacity, AP by 0.26% and AP75 by 1.28% on PASCAL VOC, and AP by 0.06% and AP75 by 0.65% on MS COCO.

Huber Loss function is a regression type loss function, mainly used for optimization problems.In order to make the predicted value close to the true value and minimize the distance between them, the traditional loss function generally uses the gradient descent method to find the minimum value. However, the gradient descent method takes too long and consumes a lot of memory. It may not necessarily find the global optimal value, and it is easy to fall into the problem of local optimization. The data of the unconstrained function is complicated and huge, and the Huber Loss function sets the hyper-parameter δ to optimize MSE and MAE, we must iterate continuously to train the hyper-parameters to obtain more accurate parameter values, which will cause a problem of large amount of calculations. The beetle antennae search algorithm is a simple biological intelligence optimization algorithm that can provide the best solution based on huge data, with fast convergence speed, small amount of calculation, simple operation, and no need to know the specific function. In order to improve the accuracy of finding the global optimal value, this paper changed the traditional fixed-step antennae search algorithm to variable-step beetle antennae search algorithm. This article will discuss the application of the gradient descent method in the regression loss function, and then use the variable step size beetle antennae search algorithm to optimize Huber Loss function.

Arbitrary-oriented objects exist widely in remote sensing images. The mainstream rotation detectors use oriented bounding boxes (OBBs) or quadrilateral bounding boxes (QBBs) to represent the rotating objects. However, these methods suffer from the representation ambiguity for oriented object definition, which leads to suboptimal regression optimization and the inconsistency between the loss metric and the localization accuracy of the predictions. In this letter, we propose a representation invariance loss (RIL) to optimize the bounding box regression for the rotating objects in the remote sensing images. RIL treats multiple representations of an oriented object as multiple equivalent local minima and hence transforms bounding box regression into an adaptive matching process with these local minima. Next, the Hungarian matching algorithm is adopted to obtain the optimal regression strategy. Besides, we propose a normalized rotation loss to alleviate the weak correlation between different variables and their unbalanced loss contribution in OBB representation. Extensive experiments on remote sensing datasets show that our method achieves consistent and substantial improvement. The code and models are available at <uri>https://github.com/ming71/RIDet</uri> to facilitate future research.

An improved Yolov5s based on transformer backbone network for detection and classification of bronchoalveolar lavage cells

During the manufacturing process of printed circuit boards (PCBs), quality defects can occur, which can affect the performance and reliability of PCBs. Existing deep learning-based PCB defect detection methods are difficult to simultaneously achieve the goals of high detection accuracy, fast detection speed, and small number of parameters. Therefore, this paper proposes a PCB defect detection algorithm based on CDI-YOLO. Firstly, the coordinate attention mechanism (CA) is introduced to improve the backbone and neck network of YOLOv7-tiny, enhance the feature extraction capability of the model, and thus improve the accuracy of model detection. Secondly, DSConv is used to replace part of the common convolution in YOLOv7-tiny to achieve lower computing costs and faster detection speed. Finally, Inner-CIoU is used as the bounding box regression loss function of CDI-YOLO to speed up the bounding box regression process. The experimental results show that the method achieves 98.3% mAP on the PCB defect dataset, the detection speed is 128 frames per second (FPS), the parameters is 5.8 M, and the giga floating-point operations per second (GFLOPs) is 12.6 G. Compared with the existing methods, the comprehensive performance of this method has advantages.

In this paper, we investigate a more efficient IoU loss based bounding box localization mechanism on top of end-to-end target detection frameworks to further improve the regression accuracy of object detection methods. Aiming at the limited spatial perception ability of deep convolution features, this paper proposes an optimization strategy by combining shallow spatial feature feed-forward mechanism (SSFF) with focal IoU loss function for bounding box regression tasks in target detection. This strategy firstly constructs a channel to transfer important location information in shallow spatial features to deep spatial features to reduce the loss of spatial details. Secondly, it constructs a focal IoU loss function based on the IoU loss, which dynamically adjusts loss weights according to the regression difficulty of different bounding boxes, to improve the positioning ability of regression networks on difficult bounding boxes. The experimental results show that the proposed methods can effectively improve the regression accuracy of target detection models.

Compared with natural images, remote sensing targets have small and dense target shapes as well as complex target backgrounds. As a result, insufficient detection accuracy and target location cannot be accurately identified. So, this paper proposes the YOLO-extract algorithm based on the YOLOv5 algorithm. Firstly, The YOLO-extract algorithm optimized the model structure of the YOLOv5 algorithm. The YOLO-extract algorithm not only deleted the feature layer and prediction head with poor feature extraction ability but also a new feature extractor with stronger feature extraction ability was integrated into the network. At the same time, YOLO-extract borrowed the idea of residual network to integrate Coordinate Attention into the network. Secondly, the mixed dilated convolution was combined with the redesigned residual structure to enhance the feature and location information extraction ability of the shallow layer of the model and optimize the feature extraction ability of the model for different scale targets. Finally, drawing on the idea of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> -IoU Loss, Focal- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> EIoU Loss was designed to replace CIoU Loss, which makes the model bounding box regression faster and the loss lower. The experimental results on the test data set show that compared with the YOLOv5 algorithm, the YOLO-extract algorithm has a faster convergence speed, reduces the calculation amount by 45.3GFLOPs and the number of parameters by 10.526M, but increases the mAP by 8.1% and the detection speed by 3 times.

Indian traffic sign detection and recognition using deep learning