# IoU-aware Single-stage Object Detector for Accurate Localization

arXiv: https://arxiv.org/abs/1912.05992 · HTML: https://mlsanity.com/paper/1912.05992/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2019.

## Built on by (most cited first, 30 of 36)

- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds](https://mlsanity.com/paper/2112.09205/) (2021)
- [Object discovery and representation networks](https://mlsanity.com/paper/2203.08777/) (2022)
- [One-Stage Cascade Refinement Networks for Infrared Small Target Detection](https://mlsanity.com/paper/2212.08472/) (2022)
- [Saliency-Guided DETR for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2410.01615/) (2024)
- [Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search](https://mlsanity.com/paper/2102.04700/) (2021)
- [Self-supervised video pretraining yields robust and more human-aligned visual representations](https://mlsanity.com/paper/2210.06433/) (2022)
- [Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection](https://mlsanity.com/paper/2212.05505/) (2022)
- [Improving Object Detection by Label Assignment Distillation](https://mlsanity.com/paper/2108.10520/) (2021)
- [Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking](https://mlsanity.com/paper/2208.10976/) (2022)
- [Three ways to improve feature alignment for open vocabulary detection](https://mlsanity.com/paper/2303.13518/) (2023)
- [RGB Stream Is Enough for Temporal Action Detection](https://mlsanity.com/paper/2107.04362/) (2021)
- [D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention](https://mlsanity.com/paper/2203.00860/) (2022)
- [SCD: A Stacked Carton Dataset for Detection and Segmentation](https://mlsanity.com/paper/2102.12808/) (2021)
- [An Extendable, Efficient and Effective Transformer-based Object Detector](https://mlsanity.com/paper/2204.07962/) (2022)
- [DSLA: Dynamic smooth label assignment for efficient anchor-free object detection](https://mlsanity.com/paper/2208.00817/) (2022)
- [DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection](https://mlsanity.com/paper/2311.10437/) (2023)
- [Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness](https://mlsanity.com/paper/2107.14342/) (2021)
- [Improved Pillar with Fine-grained Feature for 3D Object Detection](https://mlsanity.com/paper/2110.06049/) (2021)
- [Are Commercial Face Detection Models as Biased as Academic Models?](https://mlsanity.com/paper/2201.10047/) (2022)
- [Gaussian Guided IoU: A Better Metric for Balanced Learning on Object Detection](https://mlsanity.com/paper/2103.13613/) (2021)
- [Pillar R-CNN for Point Cloud 3D Object Detection](https://mlsanity.com/paper/2302.13301/) (2023)
- [NIV-SSD: Neighbor IoU-Voting Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2401.12447/) (2024)
- [1st Place Solution to ICDAR 2021 RRC-ICTEXT End-to-end Text Spotting and Aesthetic Assessment on Integrated Circuit](https://mlsanity.com/paper/2104.03544/) (2021)
- [Rethinking the Misalignment Problem in Dense Object Detection](https://mlsanity.com/paper/2108.12176/) (2021)
- [GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection](https://mlsanity.com/paper/2306.17450/) (2023)
- [MDS-DETR: DETR with Masked Duplicate Suppressor](https://mlsanity.com/paper/2605.23507/) (2026)
- [Objects as Extreme Points](https://mlsanity.com/paper/2104.14066/) (2021)
- [Bounding-box deep calibration for high performance face detection](https://mlsanity.com/paper/2110.03892/) (2021)

## Abstract (arXiv)

Due to the simpleness and high efficiency, single-stage object detectors have been widely applied in many computer vision applications . However, the low correlation between the classification score and localization accuracy of the predicted detections has severely hurt the localization accuracy of models. In this paper, IoU-aware single-stage object detector is proposed to solve this problem. Specifically, IoU-aware single-stage object detector predicts the IoU for each detected box. Then the classification score and predicted IoU are multiplied to compute the final detection confidence, which is more correlated with the localization accuracy. The detection confidence is then used as the input of the subsequent NMS and COCO AP computation, which will substantially improve the localization accuracy of models. Sufficient experiments on COCO and PASCAL VOC datasets demonstrate the effectiveness of IoU-aware single-stage object detector on improving model's localization accuracy. Without whistles and bells, the proposed method can substantially improve AP by 1.7%~1.9% and AP75 by 2.2%~2.5% on COCO textittest-dev. On PASCAL VOC, the proposed method can substantially improve AP by 2.9%~4.4% and AP80, AP90 by 4.6%~10.2%. Code is available here: https://github.com/ShengkaiWu/IoU-aware-single-stage-object-detector.