# MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression

arXiv: https://arxiv.org/abs/2307.07662 · HTML: https://mlsanity.com/paper/2307.07662/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 14 Jul 2023.

## Builds on (most cited first, 30 of 42)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [PolarMask: Single Shot Instance Segmentation with Polar Representation](https://mlsanity.com/paper/1909.13226/) (2019)
- [Arbitrary-Oriented Scene Text Detection via Rotation Proposals](https://mlsanity.com/paper/1703.01086/) (2017)
- [Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes](https://mlsanity.com/paper/1908.08207/) (2019)
- [ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network](https://mlsanity.com/paper/2002.10200/) (2020)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [DSSD : Deconvolutional Single Shot Detector](https://mlsanity.com/paper/1701.06659/) (2017)
- [You Only Look One-level Feature](https://mlsanity.com/paper/2103.09460/) (2021)
- [Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training](https://mlsanity.com/paper/2004.06002/) (2020)
- [TensorMask: A Foundation for Dense Object Segmentation](https://mlsanity.com/paper/1903.12174/) (2019)
- [Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2005.03572/) (2020)

## Built on by (most cited first, 10 of 10)

- [SOD-YOLOv8 -- Enhancing YOLOv8 for Small Object Detection in Traffic Scenes](https://mlsanity.com/paper/2408.04786/) (2024)
- [PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices](https://mlsanity.com/paper/2410.21822/) (2024)
- [HGO-YOLO: Advancing Anomaly Behavior Detection with Hierarchical Features and Lightweight Optimized Detection](https://mlsanity.com/paper/2503.07371/) (2025)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [Fused attention mechanism-based ore sorting network](https://mlsanity.com/paper/2405.02785/) (2024)
- [Improved YOLOv7x-Based Defect Detection Algorithm for Power Equipment](https://mlsanity.com/paper/2502.17961/) (2025)
- [YOLO-FireAD: Efficient Fire Detection via Attention-Guided Inverted Residual Learning and Dual-Pooling Feature Preservation](https://mlsanity.com/paper/2505.20884/) (2025)
- [LAF-YOLOv10 with Partial Convolution Backbone, Attention-Guided Feature Pyramid, Auxiliary P2 Head, and Wise-IoU Loss for Small Object Detection in Drone Aerial Imagery](https://mlsanity.com/paper/2602.13378/) (2026)
- [Contour-Guided Spectral Routing for Robust Real-Time Pedestrian Detection](https://mlsanity.com/paper/2609.14383/) (2026)
- [Small Object Detection in Drone Aerial Imagery with LAF-YOLOv10](https://mlsanity.com/paper/2609.14560/) (2026)

## Abstract (arXiv)

Bounding box regression (BBR) has been widely used in object detection and instance segmentation, which is an important step in object localization. However, most of the existing loss functions for bounding box regression cannot be optimized when the predicted box has the same aspect ratio as the groundtruth box, but the width and height values are exactly different. In order to tackle the issues mentioned above, we fully explore the geometric features of horizontal rectangle and propose a novel bounding box similarity comparison metric MPDIoU based on minimum point distance, which contains all of the relevant factors considered in the existing loss functions, namely overlapping or non-overlapping area, central points distance, and deviation of width and height, while simplifying the calculation process. On this basis, we propose a bounding box regression loss function based on MPDIoU, called LMPDIoU . Experimental results show that the MPDIoU loss function is applied to state-of-the-art instance segmentation (e.g., YOLACT) and object detection (e.g., YOLOv7) model trained on PASCAL VOC, MS COCO, and IIIT5k outperforms existing loss functions.