Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
Work
Year: 2019
Type: article
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... more
Institutions The University of Adelaide, Laboratoire d'Informatique de Paris-Nord, Stanford University
Cites: 30
Cited by: 4,165
Related to: 10
FWCI: 98.09
Citation percentile (by year/subfield): 99.99
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Sustainable Development Goal Reduced inequalities
Open Access status: green