# Side-Aware Boundary Localization for More Precise Object Detection

arXiv: https://arxiv.org/abs/1912.04260 · HTML: https://mlsanity.com/paper/1912.04260/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2019.

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

- [V3Det: Vast Vocabulary Visual Detection Dataset](https://mlsanity.com/paper/2304.03752/) (2023)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [Rethinking Pseudo Labels for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.00168/) (2021)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts](https://mlsanity.com/paper/2307.12730/) (2023)
- [A Review on Deep Learning in UAV Remote Sensing](https://mlsanity.com/paper/2101.10861/) (2021)
- [Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines](https://mlsanity.com/paper/2406.14482/) (2024)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [GaTector: A Unified Framework for Gaze Object Prediction](https://mlsanity.com/paper/2112.03549/) (2021)
- [NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors](https://mlsanity.com/paper/2412.16955/) (2024)
- [Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models](https://mlsanity.com/paper/2111.07355/) (2021)
- [Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection](https://mlsanity.com/paper/2206.13728/) (2022)
- [FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network](https://mlsanity.com/paper/2108.04644/) (2021)
- [Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection](https://mlsanity.com/paper/2407.20078/) (2024)
- [SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving](https://mlsanity.com/paper/2305.06940/) (2023)
- [Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression](https://mlsanity.com/paper/2302.08662/) (2023)
- [Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History](https://mlsanity.com/paper/2301.05124/) (2023)
- [Edge-guided Representation Learning for Underwater Object Detection](https://mlsanity.com/paper/2306.00440/) (2023)
- [PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling](https://mlsanity.com/paper/2104.13876/) (2021)
- [A Gated Cross-domain Collaborative Network for Underwater Object Detection](https://mlsanity.com/paper/2306.14141/) (2023)
- [Traffic Video Object Detection using Motion Prior](https://mlsanity.com/paper/2311.10092/) (2023)
- [To Make Yourself Invisible with Adversarial Semantic Contours](https://mlsanity.com/paper/2303.00284/) (2023)
- [AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection](https://mlsanity.com/paper/2505.15184/) (2025)
- [InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee](https://mlsanity.com/paper/2208.06962/) (2022)
- [Automated Optical Inspection of FAST's Reflector Surface using Drones and Computer Vision](https://mlsanity.com/paper/2212.09039/) (2022)
- [Aedes aegypti Egg Counting with Neural Networks for Object Detection](https://mlsanity.com/paper/2403.08016/) (2024)
- [COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts](https://mlsanity.com/paper/2504.10158/) (2025)
- [HR-RCNN: Hierarchical Relational Reasoning for Object Detection](https://mlsanity.com/paper/2110.13892/) (2021)
- [Boundary Distribution Estimation for Precise Object Detection](https://mlsanity.com/paper/2111.01396/) (2021)
- [A Cross-direction Task Decoupling Network for Small Logo Detection](https://mlsanity.com/paper/2305.02503/) (2023)

## Abstract (arXiv)

Current object detection frameworks mainly rely on bounding box regression to localize objects. Despite the remarkable progress in recent years, the precision of bounding box regression remains unsatisfactory, hence limiting performance in object detection. We observe that precise localization requires careful placement of each side of the bounding box. However, the mainstream approach, which focuses on predicting centers and sizes, is not the most effective way to accomplish this task, especially when there exists displacements with large variance between the anchors and the targets. In this paper, we propose an alternative approach, named as Side-Aware Boundary Localization (SABL), where each side of the bounding box is respectively localized with a dedicated network branch. To tackle the difficulty of precise localization in the presence of displacements with large variance, we further propose a two-step localization scheme, which first predicts a range of movement through bucket prediction and then pinpoints the precise position within the predicted bucket. We test the proposed method on both two-stage and single-stage detection frameworks. Replacing the standard bounding box regression branch with the proposed design leads to significant improvements on Faster R-CNN, RetinaNet, and Cascade R-CNN, by 3.0%, 1.7%, and 0.9%, respectively. Code is available at https://github.com/open-mmlab/mmdetection.