mlsanityData to 14 Oct 2026

Acquisition of Localization Confidence for Accurate Object Detection

arXiv 1807.11590 ↗First posted 30 Jul 2018cs.CVcited by 176

Not on the map. Why?

Abstract (arXiv)

Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classification confidence, localization confidence is absent. This makes properly localized bounding boxes degenerate during iterative regression or even suppressed during NMS. In the paper we propose IoU-Net learning to predict the IoU between each detected bounding box and the matched ground-truth. The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bounding boxes. Furthermore, an optimization-based bounding box refinement method is proposed, where the predicted IoU is formulated as the objective. Extensive experiments on the MS-COCO dataset show the effectiveness of IoU-Net, as well as its compatibility with and adaptivity to several state-of-the-art object detectors.

Key facts. Cited by 176 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 59; 2022: 38; 2023: 48; 2024: 14; 2025: 8; 2026: 9.

176 papers.

Sort:

By area:

  1. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  2. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  3. 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
  4. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 127
  5. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  6. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  7. 2021Region Similarity Representation Learningcited by 96
  8. 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
  9. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  10. 2022Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baselinecited by 91
  11. 2023DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignmentcited by 90
  12. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
38 more
  1. 2021Object Tracking by Jointly Exploiting Frame and Event Domaincited by 84
  2. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  3. 2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
  4. 2021Localization Distillation for Dense Object Detectioncited by 55
  5. 2022PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detectioncited by 51
  6. 2023Compact Transformer Tracker with Correlative Masked Modelingcited by 50
  7. 2023Rank-DETR for High Quality Object Detectioncited by 50
  8. 2021Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlookcited by 46
  9. 2024Context-Guided Spatio-Temporal Video Groundingcited by 46
  10. 2021Rethinking Pseudo Labels for Semi-Supervised Object Detectioncited by 45
  11. 2023DiffusionTrack: Diffusion Model For Multi-Object Trackingcited by 40
  12. 2021Disentangle Your Dense Object Detectorcited by 37
  13. 2023Deep networks for system identification: a Surveycited by 37
  14. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  15. 2022Learning Quality-aware Dynamic Memory for Video Object Segmentationcited by 35
  16. 2021Saliency-Associated Object Trackingcited by 30
  17. 2022MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentationcited by 30
  18. 2021CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Imagescited by 29
  19. 2021Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easiercited by 27
  20. 2023Uni3DETR: Unified 3D Detection Transformercited by 27
  21. 2022WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Trackingcited by 26
  22. 2022Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarizationcited by 26
  23. 2021From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decodercited by 23
  24. 2021Rank & Sort Loss for Object Detection and Instance Segmentationcited by 22
  25. 2021Learning to Track Objects from Unlabeled Videoscited by 21
  26. 2023Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Trackingcited by 21
  27. 2024Saliency-Guided DETR for Moment Retrieval and Highlight Detectioncited by 21
  28. 2021Loss Function Discovery for Object Detection via Convergence-Simulation Driven Searchcited by 20
  29. 2022DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detectioncited by 20
  30. 2022Localization Distillation for Object Detectioncited by 19
  31. 2023Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibrationcited by 19
  32. 2023Cascade-DETR: Delving into High-Quality Universal Object Detectioncited by 19
  33. 2021Objects in Semantic Topologycited by 18
  34. 2021Combating Noise: Semi-supervised Learning by Region Uncertainty Quantificationcited by 18
  35. 2022DR.VIC: Decomposition and Reasoning for Video Individual Countingcited by 18
  36. 2022Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Trackingcited by 17
  37. 2023MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detectioncited by 17
  38. 2021RGB Stream Is Enough for Temporal Action Detectioncited by 16

50 most cited of 176 All 176 (JSON)