IoU Loss for 2D/3D Object Detection

Dingfu Zhou, Jin Fang, Xibin Song, Chenye Guan, Junbo Yin, Yuchao Dai, Ruigang Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

271 Scopus citations


In the 2D/3D object detection task, Intersection-over-Union (IoU) has been widely employed as an evaluation metric to evaluate the performance of different detectors in the testing stage. However, during the training stage, the common distance loss (e.g, L-1 or L-2) is often adopted as the loss function to minimize the discrepancy between the predicted and ground truth Bounding Box (Bbox). To eliminate the performance gap between training and testing, the IoU loss has been introduced for 2D object detection in [1] and [2]. Unfortunately, all these approaches only work for axis-aligned 2D Boxes, which cannot be applied for more general object detection task with rotated Boxes. To resolve this issue, we investigate the IoU computation for two rotated Boxes first and then implement a unified framework, IoU loss layer for both 2D and 3D object detection tasks. By integrating the implemented IoU loss into several state-of-the-art 3D object detectors, consistent improvements have been achieved for both bird-eye-view 2D detection and point cloud 3D detection on the public KITTI [3] benchmark.

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on 3D Vision, 3DV 2019
Number of pages10
ISBN (Electronic)9781728131313
StatePublished - Sep 2019
Event7th International Conference on 3D Vision, 3DV 2019 - Quebec, Canada
Duration: Sep 15 2019Sep 18 2019

Publication series

NameProceedings - 2019 International Conference on 3D Vision, 3DV 2019


Conference7th International Conference on 3D Vision, 3DV 2019

Bibliographical note

Publisher Copyright:
© 2019 IEEE.


  • 3D Object Detection
  • Autonomous Driving
  • IoU Loss

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Media Technology
  • Modeling and Simulation


Dive into the research topics of 'IoU Loss for 2D/3D Object Detection'. Together they form a unique fingerprint.

Cite this