Compression Artifact Removal with Ensemble Learning of Neural Networks
Abstract
We propose to improve the reconstruction quality of DLVC intra coding based on an ensemble of deep restoration neural networks. Different ways are proposed to generate diversity models, and based on these models, the behavior of different integration methods for model ensemble is explored. The experimental results show that model ensemble can bring additional performance gains to post-processing on the basis that deep neural networks have shown great performance improvements. Besides, we observe that both averaging and selection approaches for model ensemble can bring performance gains, and they can be used in combination to pursue better results.
Cite
Text
Hu et al. "Compression Artifact Removal with Ensemble Learning of Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00074Markdown
[Hu et al. "Compression Artifact Removal with Ensemble Learning of Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/hu2020cvprw-compression/) doi:10.1109/CVPRW50498.2020.00074BibTeX
@inproceedings{hu2020cvprw-compression,
title = {{Compression Artifact Removal with Ensemble Learning of Neural Networks}},
author = {Hu, Yueyu and Ma, Haichuan and Liu, Dong and Liu, Jiaying},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {555-559},
doi = {10.1109/CVPRW50498.2020.00074},
url = {https://mlanthology.org/cvprw/2020/hu2020cvprw-compression/}
}