# Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

arXiv: https://arxiv.org/abs/2110.13675 · HTML: https://mlsanity.com/paper/2110.13675/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 48 references that are in the map.
- First posted on arXiv 26 Oct 2021.

## Builds on (most cited first, 30 of 40)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (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)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [Normalized Loss Functions for Deep Learning with Noisy Labels](https://mlsanity.com/paper/2006.13554/) (2020)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [Dimensionality-Driven Learning with Noisy Labels](https://mlsanity.com/paper/1806.02612/) (2018)
- [Bottom-up Object Detection by Grouping Extreme and Center Points](https://mlsanity.com/paper/1901.08043/) (2019)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [Revisiting the Sibling Head in Object Detector](https://mlsanity.com/paper/2003.07540/) (2020)
- [Focal and Efficient IOU Loss for Accurate Bounding Box Regression](https://mlsanity.com/paper/2101.08158/) (2021)

## Built on by (most cited first, 18 of 18)

- [YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications](https://mlsanity.com/paper/2209.02976/) (2022)
- [Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box](https://mlsanity.com/paper/2311.02877/) (2023)
- [Enhancing Maritime Situational Awareness through End-to-End Onboard Raw Data Analysis](https://mlsanity.com/paper/2411.03403/) (2024)
- [SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebrae](https://mlsanity.com/paper/2110.15082/) (2021)
- [Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regime](https://mlsanity.com/paper/2307.09562/) (2023)
- [Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices](https://mlsanity.com/paper/2412.02171/) (2024)
- [An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection](https://mlsanity.com/paper/2203.16506/) (2022)
- [EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union](https://mlsanity.com/paper/2403.15474/) (2024)
- [Revisiting the Scale Loss Function and Gaussian-Shape Convolution for Infrared Small Target Detection](https://mlsanity.com/paper/2604.09991/) (2026)
- [Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)](https://mlsanity.com/paper/2210.12989/) (2022)
- [Unified-IoU: For High-Quality Object Detection](https://mlsanity.com/paper/2408.06636/) (2024)
- [PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices](https://mlsanity.com/paper/2410.21822/) (2024)
- [Event-RGB Fusion for Spacecraft Pose Estimation Under Harsh Lighting](https://mlsanity.com/paper/2507.05698/) (2025)
- [Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videos](https://mlsanity.com/paper/2602.12922/) (2026)
- [CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling](https://mlsanity.com/paper/2607.05177/) (2026)
- [Hybrid Classification-Regression Adaptive Loss for Dense Object Detection](https://mlsanity.com/paper/2408.17182/) (2024)
- [N-EIoU-YOLOv9: A Signal-Aware Bounding Box Regression Loss for Lightweight Mobile Detection of Rice Leaf Diseases](https://mlsanity.com/paper/2601.09170/) (2026)
- [Safety-Aligned 3D Object Detection: Single-Vehicle, Cooperative, and End-to-End Perspectives](https://mlsanity.com/paper/2604.03325/) (2026)

## Abstract (arXiv)

Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss and its variants. In this paper, we generalize existing IoU-based losses to a new family of power IoU losses that have a power IoU term and an additional power regularization term with a single power parameter α. We call this new family of losses the α-IoU losses and analyze properties such as order preservingness and loss/gradient reweighting. Experiments on multiple object detection benchmarks and models demonstrate that α-IoU losses, 1) can surpass existing IoU-based losses by a noticeable performance margin; 2) offer detectors more flexibility in achieving different levels of bbox regression accuracy by modulating α; and 3) are more robust to small datasets and noisy bboxes.