mlsanityData to 7 Oct 2026

Bounding Box Regression with Uncertainty for Accurate Object Detection

arXiv 1809.08545 ↗First posted 23 Sep 2018cs.CVcited by 143

Not on the map. Why?

Abstract (arXiv)

Large-scale object detection datasets (e.g., MS-COCO) try to define the ground truth bounding boxes as clear as possible. However, we observe that ambiguities are still introduced when labeling the bounding boxes. In this paper, we propose a novel bounding box regression loss for learning bounding box transformation and localization variance together. Our loss greatly improves the localization accuracies of various architectures with nearly no additional computation. The learned localization variance allows us to merge neighboring bounding boxes during non-maximum suppression (NMS), which further improves the localization performance. On MS-COCO, we boost the Average Precision (AP) of VGG-16 Faster R-CNN from 23.6% to 29.1%. More importantly, for ResNet-50-FPN Mask R-CNN, our method improves the AP and AP90 by 1.8% and 6.2% respectively, which significantly outperforms previous state-of-the-art bounding box refinement methods. Our code and models are available at: github.com/yihui-he/KL-Loss

Key facts. Cited by 143 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 43; 2022: 31; 2023: 31; 2024: 17; 2025: 12; 2026: 9.

143 papers.

Sort:

By area:

  1. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  2. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  3. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  4. 2024Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstructioncited by 100
  5. 2021MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagationcited by 82
  6. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  7. 2022AdaMixer: A Fast-Converging Query-Based Object Detectorcited by 78
  8. 2022Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectorscited by 69
  9. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  10. 2023MFT: Long-Term Tracking of Every Pixelcited by 61
  11. 2021Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regressioncited by 58
  12. 2021Localization Distillation for Dense Object Detectioncited by 55
38 more
  1. 2021Adaptive Class Suppression Loss for Long-Tail Object Detectioncited by 55
  2. 2022Few-shot Object Counting and Detectioncited by 55
  3. 2021EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detectioncited by 49
  4. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  5. 2022Uncertainty Quantification of Collaborative Detection for Self-Drivingcited by 46
  6. 2021Rethinking Pseudo Labels for Semi-Supervised Object Detectioncited by 45
  7. 2022OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regressioncited by 44
  8. 2021Spatial Uncertainty-Aware Semi-Supervised Crowd Countingcited by 38
  9. 2021Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectorscited by 37
  10. 2023Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecastingcited by 33
  11. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 33
  12. 2021SOLO: A Simple Framework for Instance Segmentationcited by 32
  13. 2025HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrievalcited by 32
  14. 2021CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Imagescited by 29
  15. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  16. 2023Collaborative Multi-Object Tracking with Conformal Uncertainty Propagationcited by 27
  17. 2021Uncertainty for Identifying Open-Set Errors in Visual Object Detectioncited by 26
  18. 2024SARATR-X: Toward Building A Foundation Model for SAR Target Recognitioncited by 25
  19. 2021A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applicationscited by 24
  20. 2022GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimationcited by 24
  21. 2024Adaptive Bounding Box Uncertainties via Two-Step Conformal Predictioncited by 23
  22. 2021Rank & Sort Loss for Object Detection and Instance Segmentationcited by 22
  23. 2022Representation Uncertainty in Self-Supervised Learning as Variational Inferencecited by 22
  24. 2023Calibrating Uncertainty for Semi-Supervised Crowd Countingcited by 22
  25. 2022Robust Object Detection With Inaccurate Bounding Boxescited by 20
  26. 2022Localization Distillation for Object Detectioncited by 19
  27. 2022iFS-RCNN: An Incremental Few-shot Instance Segmentercited by 19
  28. 2023Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibrationcited by 19
  29. 2024ScanFormer: Referring Expression Comprehension by Iteratively Scanningcited by 18
  30. 2023MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detectioncited by 17
  31. 2021I Find Your Lack of Uncertainty in Computer Vision Disturbingcited by 16
  32. 2021Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectorscited by 16
  33. 2021Circle Representation for Medical Object Detectioncited by 15
  34. 2021Autoregressive Quantile Flows for Predictive Uncertainty Estimationcited by 15
  35. 2022You Should Look at All Objectscited by 12
  36. 2021Robust Monocular Localization in Sparse HD Maps Leveraging Multi-Task Uncertainty Estimationcited by 11
  37. 2021Improved YOLOv5 network for real-time multi-scale traffic sign detectioncited by 11
  38. 2023MUBen: Benchmarking the Uncertainty of Molecular Representation Modelscited by 11

50 most cited of 143 All 143 (JSON)