Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
Authors:
Top Cited Papers
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 658-666
Abstract
Intersection over Union (IoU) is the most popular evaluation metric used in the object detection benchmarks. However, there is a gap between optimizing the commonly used distance losses for regressing the parameters of a bounding box and maximizing this metric value. The optimal objective for a metric is the metric itself. In the case of axis-aligned 2D bounding boxes, it can be shown that IoU can be directly used as a regression loss. However, IoU has a plateau making it infeasible to optimize in the case of non-overlapping bounding boxes. In this paper, we address the this weakness by introducing a generalized version of IoU as both a new loss and a new metric. By incorporating this generalized IoU ( GIoU) as a loss into the state-of-the art object detection frameworks, we show a consistent improvement on their performance using both the standard, IoU based, and new, GIoU based, performance measures on popular object detection benchmarks such as PASCAL VOC and MS COCO.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Mask R-CNN2017
- Feature Pyramid Networks for Object Detection2017
- Scene Parsing through ADE20K Dataset2017
- UnitBox2016
- Deep Residual Learning for Image Recognition2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009