mlsanityData to 14 Oct 2026

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

arXiv 2110.13675 ↗First posted 26 Oct 2021cs.CVcited by 18

Not on the map. Why?

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.

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

40 of 48 references.

References · 40

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2017Mask R-CNNcited by 7,277
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  7. 2015Fast R-CNNcited by 2,933
  8. 2018YOLOv3: An Incremental Improvementcited by 2,659
  9. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  10. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  11. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  12. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
28 more
  1. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  2. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  3. 2019Objects as Pointscited by 1,175
  4. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  5. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  6. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  7. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  8. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  9. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  10. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  11. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 459
  12. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  13. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  14. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  15. 2019Bottom-up Object Detection by Grouping Extreme and Center Pointscited by 156
  16. 2019A Robust Learning Approach to Domain Adaptive Object Detectioncited by 109
  17. 2020Revisiting the Sibling Head in Object Detectorcited by 82
  18. 2021Focal and Efficient IOU Loss for Accurate Bounding Box Regressioncited by 57
  19. 2020CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detectioncited by 41
  20. 2018NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detectioncited by 37
  21. 2019Learning from Noisy Anchors for One-stage Object Detectioncited by 35
  22. 2017Improving Object Localization with Fitness NMS and Bounded IoU Losscited by 31
  23. 2020Towards Noise-resistant Object Detection with Noisy Annotationscited by 25
  24. 2021Loss Function Discovery for Object Detection via Convergence-Simulation Driven Searchcited by 20
  25. 2021AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Taskscited by 19
  26. 2020Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentationcited by 16
  27. 2020Single-Shot Two-Pronged Detector with Rectified IoU Losscited by 5
  28. 2020Learning Non-Unique Segmentation with Reward-Penalty Dice Losscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 2; 2024: 6; 2025: 1; 2026: 5.

18 papers.

Sort:

By area:

  1. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 275
  2. 2023Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Boxcited by 9
  3. 2024Enhancing Maritime Situational Awareness through End-to-End Onboard Raw Data Analysiscited by 5
  4. 2021SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebraecited by 3
  5. 2023Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regimecited by 3
  6. 2024Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devicescited by 3
  7. 2022An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detectioncited by 2
  8. 2024EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Unioncited by 2
  9. 2026Revisiting the Scale Loss Function and Gaussian-Shape Convolution for Infrared Small Target Detectioncited by 2
  10. 2022Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)cited by 1
  11. 2024Unified-IoU: For High-Quality Object Detectioncited by 1
  12. 2024PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slicescited by 1
6 more
  1. 2025Event-RGB Fusion for Spacecraft Pose Estimation Under Harsh Lightingcited by 1
  2. 2026Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videoscited by 1
  3. 2026CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Schedulingcited by 1
  4. 2024Hybrid Classification-Regression Adaptive Loss for Dense Object Detectioncited by 0
  5. 2026N-EIoU-YOLOv9: A Signal-Aware Bounding Box Regression Loss for Lightweight Mobile Detection of Rice Leaf Diseasescited by 0
  6. 2026Safety-Aligned 3D Object Detection: Single-Vehicle, Cooperative, and End-to-End Perspectivescited by 0