Superkernel Neural Architecture Search for Image Denoising
Abstract
Recent advancements in Neural Architecture Search (NAS) resulted in finding new state-of-the-art Artificial Neural Network (ANN) solutions for tasks like image classification, object detection, or semantic segmentation without substantial human supervision. In this paper, we focus on exploring NAS for a dense prediction task that is image denoising. Due to a costly training procedure, most NAS solutions for image enhancement rely on reinforcement learning or evolutionary algorithm exploration, which usually take weeks (or even months) to train. Therefore, we introduce a new efficient implementation of various superkernel techniques that enable fast (6-8 RTX2080 GPU hours) single-shot training of models for dense predictions. We demonstrate the effectiveness of our method on the SIDD+ benchmark for image denoising [3].
Cite
Text
Mozejko et al. "Superkernel Neural Architecture Search for Image Denoising." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00250Markdown
[Mozejko et al. "Superkernel Neural Architecture Search for Image Denoising." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/mozejko2020cvprw-superkernel/) doi:10.1109/CVPRW50498.2020.00250BibTeX
@inproceedings{mozejko2020cvprw-superkernel,
title = {{Superkernel Neural Architecture Search for Image Denoising}},
author = {Mozejko, Marcin and Latkowski, Tomasz and Treszczotko, Lukasz and Szafraniuk, Michal and Trojanowski, Krzysztof},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {2002-2011},
doi = {10.1109/CVPRW50498.2020.00250},
url = {https://mlanthology.org/cvprw/2020/mozejko2020cvprw-superkernel/}
}