Image quality assessment based label smoothing in deep neural network learning

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...

Szczegółowa specyfikacja

Opis bibliograficzny
1. autor: Chen, Zhou
Kolejni autorzy: School of Computer Science and Engineering
Format: Research Report
Język:English
Wydane: 2018
Hasła przedmiotowe:
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Dostęp online:http://hdl.handle.net/10356/73386

Internet

http://hdl.handle.net/10356/73386

Podobne zapisy