Erroneous pixel prediction for semantic image segmentation

Abstract We consider semantic image segmentation. Our method is inspired by Bayesian deep learning which improves image segmentation accuracy by modeling the uncertainty of the network output. In contrast to uncertainty, our method directly learns to predict the erroneous pixels of a segmentation ne...

Full description

Bibliographic Details
Main Authors: Lixue Gong, Yiqun Zhang, Yunke Zhang, Yin Yang, Weiwei Xu
Format: Article
Language:English
Published: SpringerOpen 2021-10-01
Series:Computational Visual Media
Subjects:
Online Access:https://doi.org/10.1007/s41095-021-0235-7