Papers › Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression

Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression

22 Mar 2021arXiv:2103.11696archive 2025-07-28

Dong Chen, Duoqian Miao

Numerous improvements for feedback mechanisms have contributed to the great progress in object detection. In this paper, we first present an evaluation-feedback module, which is proposed to consist of evaluation system and feedback mechanism. Then we analyze and summarize the disadvantages and improvements of traditional evaluation-feedback module. Finally, we focus on both the evaluation system and the feedback mechanism, and propose Control Distance IoU and Control Distance IoU loss function (or CDIoU and CDIoU loss for short) without increasing parameters or FLOPs in models, which show different significant enhancements on several classical and emerging models. Some experiments and comparative tests show that coordinated evaluation-feedback module can effectively improve model performance. CDIoU and CDIoU loss have different excellent performances in several models such as Faster R-CNN, YOLOv4, RetinaNet and ATSS. There is a maximum AP improvement of 1.9% and an average AP of 0.8% improvement on MS COCO dataset, compared to traditional evaluation-feedback modules.

PaperPDFCode

Code

Alan-D-Chen/CDIoU-CDIoUloss officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object Detectionobject-detectionregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionATSSAverage PoolingBatch NormalizationBottom-up Path AugmentationCSPDarknet53ConvolutionCosine AnnealingCutMixDropBlockFPNFaster R-CNNFocal LossGlobal Average PoolingGrid SensitiveLabel SmoothingLogistic RegressionMax PoolingPAFPNRPNReLUResidual ConnectionRetinaNetRoIPoolSigmoid ActivationSoftmaxSpatial Pyramid PoolingTanh ActivationYOLOv3YOLOv4k-Means Clustering

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections