Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression
| Autor: | Ian Reid, Nathan Tsoi, Amir Sadeghian, Silvio Savarese, JunYoung Gwak, Hamid Rezatofighi |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer science business.industry Intersection (set theory) Deep learning Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Regression analysis Pascal (programming language) Object detection Machine Learning (cs.LG) Artificial Intelligence (cs.AI) Minimum bounding box Metric (mathematics) Artificial intelligence business Algorithm computer computer.programming_language |
| Zdroj: | CVPR |
| DOI: | 10.48550/arxiv.1902.09630 |
| Popis: | 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 weaknesses of $IoU$ by introducing a generalized version 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. Comment: accepted in CVPR 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|