Superkernel Neural Architecture Search for Image Denoising

Marcin Mozejko, Tomasz Latkowski, Lukasz Treszczotko, Michal Szafraniuk, Krzysztof Trojanowski; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 484-485

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Mozejko_2020_CVPR_Workshops,
author = {Mozejko, Marcin and Latkowski, Tomasz and Treszczotko, Lukasz and Szafraniuk, Michal and Trojanowski, Krzysztof},
title = {Superkernel Neural Architecture Search for Image Denoising},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020}
}