Deep Separable Convolution Neural Network for Illumination Estimation

Minquan Wang, Zhaowei Shang

2019

Abstract

Illumination estimation has been studied for a long time. The algorithms to solve the problem can be roughly divided into two categories: statistical-based and learning-based. Statistical-based algorithm has the advantage of fast computing speed but low accuracy. Learning-based algorithm improve the estimation accuracy to some extent, but generally have high computational complexity and storage space. In this paper, a new deep convolution neural network is proposed. We design the network with more layers (11 convolution layers) than the existing methods, remove the “skip connection” and “Global Average Pooling” is used to replace “Fully Connection” layer which is commonly used in the existing methods. We use the separable convolution instead of the standard convolution to reduce the number of parameters. In reprocessed Color Checker Dataset, compared with the present state-of-the-art the proposed method reduces the average angular error by about 60%. At the same time, using separable convolution and “Global Average Pooling” reduces the number of parameters by about 86% compared with do not use them.

Download


Paper Citation


in Harvard Style

Wang M. and Shang Z. (2019). Deep Separable Convolution Neural Network for Illumination Estimation.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 879-886. DOI: 10.5220/0007684308790886


in Bibtex Style

@conference{icaart19,
author={Minquan Wang and Zhaowei Shang},
title={Deep Separable Convolution Neural Network for Illumination Estimation},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={879-886},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007684308790886},
isbn={978-989-758-350-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Deep Separable Convolution Neural Network for Illumination Estimation
SN - 978-989-758-350-6
AU - Wang M.
AU - Shang Z.
PY - 2019
SP - 879
EP - 886
DO - 10.5220/0007684308790886