Image quality assessment based label smoothing in deep neural network learning

For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in real application scenarios, while the practical issues regardi...

Full description

Saved in:
Bibliographic Details
Main Author: Chen, Zhou
Other Authors: School of Computer Science and Engineering
Format: Research Report
Language:English
Published: 2018
Subjects:
Online Access:http://hdl.handle.net/10356/73386
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English

Similar Items