Effect of Visual Context Information for Super Resolution Problems

Date

2019-04-26

Author

Akar, Gözde
Özkan, Savaş
Aykut, Ekin
Cengiz, Baran
Bocek, Kadircan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

33
views

0
downloads

Cite This

In this study, the effect of visual context information to the performance of learning-based techniques for the super resolution problem is analyzed. Beside the interpretation of the experimental results in detail, its theoretical reasoning is also achieved in the paper. For the experiments, two different visual datasets composed of natural and remote sensing scenes are utilized. From the experimental results, we observe that keeping visual context information in the course of parameter learning for convolutional neural networks yields better performance compared to the baselines. Moreover, we summarize that fine-tuning pre-trained parameters with the related context yet fewer samples improves the results.

Subject Keywords

Deep learning, Convolutional neural networks, Super resolution

URI

https://hdl.handle.net/11511/47806

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar