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.
@article{arxiv.2004.08870,
title = {Superkernel Neural Architecture Search for Image Denoising},
author = {Marcin Możejko and Tomasz Latkowski and Łukasz Treszczotko and Michał Szafraniuk and Krzysztof Trojanowski},
journal= {arXiv preprint arXiv:2004.08870},
year = {2020}
}