mlsanityData to 7 Oct 2026

Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression

arXiv 1902.09630 ↗First posted 25 Feb 2019cs.CV cs.AI cs.LGcited by 1,361

Not on the map. Why?

Cited by 51 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Intersection over Union (IoU) is the most popular evaluation metric used in the object detection benchmarks. However, there is a gap between optimizing the commonly used distance losses for regressing the parameters of a bounding box and maximizing this metric value. The optimal objective for a metric is the metric itself. In the case of axis-aligned 2D bounding boxes, it can be shown that IoU can be directly used as a regression loss. However, IoU has a plateau making it infeasible to optimize in the case of non-overlapping bounding boxes. In this paper, we address the weaknesses of IoU by introducing a generalized version as both a new loss and a new metric. By incorporating this generalized IoU (GIoU) as a loss into the state-of-the art object detection frameworks, we show a consistent improvement on their performance using both the standard, IoU based, and new, GIoU based, performance measures on popular object detection benchmarks such as PASCAL VOC and MS COCO.

Key facts. Cited by 1,361 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 165; 2022: 231; 2023: 297; 2024: 263; 2025: 231; 2026: 174.

1,361 papers.

Sort:

By area:

  1. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  2. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  3. 2022Planning-oriented Autonomous Drivingcited by 1,068
  4. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  5. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  6. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  7. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  8. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  9. 2021Conditional DETR for Fast Training Convergencecited by 422
  10. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  11. 2021Deep Long-Tailed Learning: A Surveycited by 416
  12. 2021Transformer Trackingcited by 412
38 more
  1. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  2. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  3. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 348
  4. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  5. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
  6. 2022Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Frameworkcited by 328
  7. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 308
  8. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  9. 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 278
  10. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  11. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  12. 2021TransVG: End-to-End Visual Grounding with Transformerscited by 269
  13. 2021Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Conceptscited by 255
  14. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 243
  15. 2022Open-Vocabulary DETR with Conditional Matchingcited by 220
  16. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  17. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  18. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  19. 2023UniVTG: Towards Unified Video-Language Temporal Groundingcited by 189
  20. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  21. 2022Language as Queries for Referring Video Object Segmentationcited by 180
  22. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 177
  23. 2022DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detectioncited by 176
  24. 2021Multimodal Virtual Point 3D Detectioncited by 166
  25. 2023Query-Dependent Video Representation for Moment Retrieval and Highlight Detectioncited by 166
  26. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  27. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  28. 2021QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Informationcited by 147
  29. 2021Referring Transformer: A One-step Approach to Multi-task Visual Groundingcited by 143
  30. 2023TriDet: Temporal Action Detection with Relative Boundary Modelingcited by 141
  31. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  32. 2022SeqTR: A Simple yet Universal Network for Visual Groundingcited by 138
  33. 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
  34. 2023LLM4Drive: A Survey of Large Language Models for Autonomous Drivingcited by 136
  35. 2021End-to-End Human Object Interaction Detection with HOI Transformercited by 134
  36. 2021End-to-End Dense Video Captioning with Parallel Decodingcited by 133
  37. 2021Probabilistic two-stage detectioncited by 130
  38. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130

50 most cited of 1,361 All 1,361 (JSON)