VISOR-NET: Visibility Estimation Based on Deep Ordinal Relative Learning under Discrete-Level Labels

VISOR-NET: Visibility Estimation Based on Deep Ordinal Relative Learning under Discrete-Level Labels

This paper proposes a novel end-to-end pipeline that uses the ordinal information and relative relation of images for visibility estimation (VISOR-NET). By encoding ordinal information into a set of relatively ordered image pairs, VISOR-NET can learn a global ranking function effectively. Due to the...

Full description

Bibliographic Details
Main Authors: Lina Xun, Huichao Zhang, Qing Yan, Qi Wu, Jun Zhang
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Sensors
Subjects:
deep learning
ordinal regression
relative learning
visibility estimation
Online Access:https://www.mdpi.com/1424-8220/22/16/6227

Internet

https://www.mdpi.com/1424-8220/22/16/6227

Similar Items