mlsanityData to 7 Oct 2026

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

arXiv 1911.08287 ↗First posted 19 Nov 2019cs.CVcited by 454

Not on the map. Why?

Abstract (arXiv)

Bounding box regression is the crucial step in object detection. In existing methods, while ℓn-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recently, IoU loss and generalized IoU (GIoU) loss have been proposed to benefit the IoU metric, but still suffer from the problems of slow convergence and inaccurate regression. In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training than IoU and GIoU losses. Furthermore, this paper summarizes three geometric factors in bounding box regression, ie, overlap area, central point distance and aspect ratio, based on which a Complete IoU (CIoU) loss is proposed, thereby leading to faster convergence and better performance. By incorporating DIoU and CIoU losses into state-of-the-art object detection algorithms, e.g., YOLO v3, SSD and Faster RCNN, we achieve notable performance gains in terms of not only IoU metric but also GIoU metric. Moreover, DIoU can be easily adopted into non-maximum suppression (NMS) to act as the criterion, further boosting performance improvement. The source code and trained models are available at https://github.com/Zzh-tju/DIoU.

Key facts. Cited by 454 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 71; 2022: 72; 2023: 85; 2024: 95; 2025: 82; 2026: 49.

454 papers.

Sort:

By area:

  1. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  2. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  3. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  4. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  5. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 308
  6. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  7. 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 278
  8. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  9. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  10. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  11. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  12. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
38 more
  1. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  2. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  3. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  4. 2024LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Modelscited by 94
  5. 2023Real-Time Flying Object Detection with YOLOv8cited by 93
  6. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
  7. 2021YOLOP: You Only Look Once for Panoptic Driving Perceptioncited by 82
  8. 2022TALLFormer: Temporal Action Localization with a Long-memory Transformercited by 78
  9. 2022The KFIoU Loss for Rotated Object Detectioncited by 73
  10. 2024Infrared Small Target Detection with Scale and Location Sensitivitycited by 70
  11. 2022YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Losscited by 66
  12. 2022Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Spacecited by 66
  13. 2023UnLoc: A Unified Framework for Video Localization Taskscited by 66
  14. 2023Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Reviewcited by 62
  15. 2023Grounded Question-Answering in Long Egocentric Videoscited by 62
  16. 2021Focal and Efficient IOU Loss for Accurate Bounding Box Regressioncited by 57
  17. 2022Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmarkcited by 56
  18. 2021Localization Distillation for Dense Object Detectioncited by 55
  19. 2021A Normalized Gaussian Wasserstein Distance for Tiny Object Detectioncited by 52
  20. 2022SIoU Loss: More Powerful Learning for Bounding Box Regressioncited by 49
  21. 2023Epic-Sounds: A Large-scale Dataset of Actions That Soundcited by 47
  22. 2022NeRF-RPN: A general framework for object detection in NeRFscited by 46
  23. 2021YOLO5Face: Why Reinventing a Face Detectorcited by 44
  24. 2022Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gapcited by 44
  25. 2023UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensationcited by 42
  26. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  27. 2021Disentangle Your Dense Object Detectorcited by 37
  28. 2022Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalizationcited by 36
  29. 2024SnAG: Scalable and Accurate Video Groundingcited by 36
  30. 2024LW-DETR: A Transformer Replacement to YOLO for Real-Time Detectioncited by 36
  31. 2024MS-DETR: Efficient DETR Training with Mixed Supervisioncited by 34
  32. 2023YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detectioncited by 33
  33. 2023Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanismcited by 30
  34. 2023Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sportscited by 29
  35. 2022BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detectioncited by 28
  36. 2023Action Sensitivity Learning for Temporal Action Localizationcited by 28
  37. 2023TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localizationcited by 27
  38. 2024LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Networkcited by 27

50 most cited of 454 All 454 (JSON)