# Acquisition of Localization Confidence for Accurate Object Detection

arXiv: https://arxiv.org/abs/1807.11590 · HTML: https://mlsanity.com/paper/1807.11590/

## Key facts

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

## Built on by (most cited first, 30 of 176)

- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [AiATrack: Attention in Attention for Transformer Visual Tracking](https://mlsanity.com/paper/2207.09603/) (2022)
- [Hierarchical Aggregation for 3D Instance Segmentation](https://mlsanity.com/paper/2108.02350/) (2021)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [Improving 3D Object Detection with Channel-wise Transformer](https://mlsanity.com/paper/2108.10723/) (2021)
- [Region Similarity Representation Learning](https://mlsanity.com/paper/2103.12902/) (2021)
- [TPCN: Temporal Point Cloud Networks for Motion Forecasting](https://mlsanity.com/paper/2103.03067/) (2021)
- [STMTrack: Template-free Visual Tracking with Space-time Memory Networks](https://mlsanity.com/paper/2104.00324/) (2021)
- [Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline](https://mlsanity.com/paper/2204.04120/) (2022)
- [DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment](https://mlsanity.com/paper/2304.04514/) (2023)
- [AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds](https://mlsanity.com/paper/2112.09205/) (2021)
- [Object Tracking by Jointly Exploiting Frame and Event Domain](https://mlsanity.com/paper/2109.09052/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Behind the Curtain: Learning Occluded Shapes for 3D Object Detection](https://mlsanity.com/paper/2112.02205/) (2021)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection](https://mlsanity.com/paper/2203.16317/) (2022)
- [Compact Transformer Tracker with Correlative Masked Modeling](https://mlsanity.com/paper/2301.10938/) (2023)
- [Rank-DETR for High Quality Object Detection](https://mlsanity.com/paper/2310.08854/) (2023)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [Context-Guided Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2401.01578/) (2024)
- [Rethinking Pseudo Labels for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.00168/) (2021)
- [DiffusionTrack: Diffusion Model For Multi-Object Tracking](https://mlsanity.com/paper/2308.09905/) (2023)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [Deep networks for system identification: a Survey](https://mlsanity.com/paper/2301.12832/) (2023)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Learning Quality-aware Dynamic Memory for Video Object Segmentation](https://mlsanity.com/paper/2207.07922/) (2022)
- [Saliency-Associated Object Tracking](https://mlsanity.com/paper/2108.03637/) (2021)
- [MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation](https://mlsanity.com/paper/2203.14662/) (2022)
- [CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2101.06849/) (2021)

## 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.