A Scale Balanced Loss for Bounding Box Regression

A Scale Balanced Loss for Bounding Box Regression

Object detectors typically use bounding box regressors to improve the accuracy of object localization. Currently, the two types of bounding box regression loss are &#x2113;<sub>n</sub>-norm-based and intersection over union (IoU)-based. However, we found that these two types of losse...

Full description

Bibliographic Details
Main Authors: Degang Sun, Yang Yang, Min Li, Jian Yang, Bo Meng, Ruwen Bai, Linghan Li, Junxing Ren
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Object detection
bounding box
regression loss
scale imbalance
Online Access:https://ieeexplore.ieee.org/document/9112187/

Internet

https://ieeexplore.ieee.org/document/9112187/

Similar Items