Back to Search Start Over

Deep Learning with Inaccurate Training Data for Image Restoration

Authors :
Liu, Bolin
Shu, Xiao
Wu, Xiaolin
Publication Year :
2018

Abstract

In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one is forced to use synthesized paired data to train the deep convolutional neural network (DCNN). However, due to the unavoidable generalization error in statistical learning, the synthetically trained DCNN often performs poorly on real world data. To overcome this problem, we propose a new general training method that can compensate for, to a large extent, the generalization errors of synthetically trained DCNNs.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1811.07268
Document Type :
Working Paper