SIoU Loss: More Powerful Learning for Bounding Box Regression

By Zhora Gevorgyan. arXiv.org, 2022

1,031 citations recorded by the source corpus.

The effectiveness of Object Detection, one of the central problems in computer vision tasks, highly depends on the definition of the loss function — a measure of how accurately your ML model can predict the expected outcome. Conventional object detection loss functions depend on aggregation of metrics of bounding box regression such as the distance, overlap area and aspect ratio of the predicted and ground truth boxes (i.e. GIoU, CIoU, ICIoU etc). However, none of the methods proposed and used to date considers the direction of the mismatch between the desired ground box and the predicted, “experimental” box. This shortage results in slower and less effective convergence as the predicted box can “wander around” during the training process and eventually end up producing a worse model. In this paper a new loss function SIoU was suggested, where penalty metrics were redefined considering the angle of the vector between the desired regression. Applied to conventional Neural Networks and datasets it is shown that SIoU improves both the speed of training and the accuracy of the inference. The effectiveness of the proposed loss function was revealed in a number of simulations and tests. In particular, the application of SIoU to the COCO-train/COCO-val results in improvements of +2.4% (mAP@0.5:0.95) and +3.6%(mAP@0.5) over other Loss Functions.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/406b457cf2dc9a62417b05b755ef5434df0a4d33

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond (2023, methodology): “They used a classiﬁcation VariFocal loss [89] and a SIoU [90]/GIoU [91] regression loss.”
Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box (2023, methodology): “The experiment compared the CIoU [3] method and SIoU [5] method, using YOLOv7-tiny [13] as the detector, VOC2007 trainval and VOC2012 trainval as the training set and VOC2007 test as the test set [20].”
A review of convolutional neural networks in computer vision (2024, positive): “The anchor-free paradigm is employed as the training approach, and to further increase the detection accuracy, the SimOTA (Ge et al. 2021) label assignment technique and SIoU (Gevorgyan 2022) bounding box regression loss are included.”
Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism (2023, methodology): “Scylla IoU: Gevorgyan [19] proved that the center-aligned anchor box would have a faster convergence speed, and constructed SIoU in terms of angle cost, distance cost, and shape cost.”
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications (2022, methodology): “We experiment with GIoU, CIoU and SIoU in this work.”
A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS (2023, neutral): “[102]/GIoU [103] regression loss.”
UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios (2023, background): “SIoU [38] introduces the angle between the predicted box and the real box as a penalty factor for the first time.”