@inproceedings{e1c4cc481099454d9bbdb9713f575950,
title = "HNAS: Hyper neural architecture search for image segmentation",
abstract = "Deep learning is a well suited approach to successfully address image processing and there are several Neural Networks architectures proposed on this research field, one interesting example is the U-net architecture and and its variants. This work proposes to automatically find the best architecture combination from a set of the current most relevant U-net architectures by using a genetic algorithm (GA) applied to solve the Retinal Blood Vessel Segmentation (RVS), which it is relevant to diagnose and cure blindness in diabetes patients. Interestingly, the experimental results show that avoiding human-bias in the design, GA finds novel combinations of U-net architectures, which at first sight seems to be complex but it turns out to be smaller, reaching competitive performance than the manually designed architectures and reducing considerably the computational effort to evolve them.",
keywords = "Image segmentation, Neural architecture search, U-Net",
author = "Yassir Houreh and Mahsa Mahdinejad and Enrique Naredo and Dias, {Douglas Mota} and Conor Ryan",
note = "Publisher Copyright: {\textcopyright} 2021 by SCITEPRESS - Science and Technology Publications, Lda.; 13th International Conference on Agents and Artificial Intelligence, ICAART 2021 ; Conference date: 04-02-2021 Through 06-02-2021",
year = "2021",
language = "English",
series = "ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence",
publisher = "SciTePress",
pages = "246--256",
editor = "Rocha, {Ana Paula} and Luc Steels and {van den Herik}, Jaap",
booktitle = "ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence",
}