Automatic Development of Deep Learning Architectures for Image Segmentation

Sergiu Cosmin Nistor, Tudor Alexandru Ileni and Adrian Sergiu Dărăbant
Additional contact information
Sergiu Cosmin Nistor: Department of Computer Science, Babeș-Bolyai University, 400084 Cluj-Napoca, Romania
Tudor Alexandru Ileni: Department of Computer Science, Babeș-Bolyai University, 400084 Cluj-Napoca, Romania
Adrian Sergiu Dărăbant: Department of Computer Science, Babeș-Bolyai University, 400084 Cluj-Napoca, Romania

Sustainability, 2020, vol. 12, issue 22, 1-18

Abstract: Machine learning is a branch of artificial intelligence that has gained a lot of traction in the last years due to advances in deep neural networks. These algorithms can be used to process large quantities of data, which would be impossible to handle manually. Often, the algorithms and methods needed for solving these tasks are problem dependent. We propose an automatic method for creating new convolutional neural network architectures which are specifically designed to solve a given problem. We describe our method in detail and we explain its reduced carbon footprint, computation time and cost compared to a manual approach. Our method uses a rewarding mechanism for creating networks with good performance and so gradually improves its architecture proposals. The application for the algorithm that we chose for this paper is segmentation of eyeglasses from images, but our method is applicable, to a larger or lesser extent, to any image processing task. We present and discuss our results, including the architecture that obtained 0.9683 intersection-over-union (IOU) score on our most complex dataset.

Keywords: convolutional neural network; image segmentation; neural architecture search; recurrent neural network; sustainable development (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/2071-1050/12/22/9707/pdf (application/pdf)
https://www.mdpi.com/2071-1050/12/22/9707/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:12:y:2020:i:22:p:9707-:d:448572

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().