Next Article in Journal
How (Un)sustainable Environments Are Related to the Diffusion of COVID-19: The Relation between Coronavirus Disease 2019, Air Pollution, Wind Resource and Energy
Next Article in Special Issue
Lookup Table and Neural Network Hybrid Strategy for Wind Turbine Pitch Control
Previous Article in Journal
Food Waste Behavior among Romanian Consumers: A Cluster Analysis
Previous Article in Special Issue
Revisiting the Contested Role of Natural Resources in Violent Conflict Risk through Machine Learning
 
 
Article

Automatic Development of Deep Learning Architectures for Image Segmentation

Department of Computer Science, Babeș-Bolyai University, 400084 Cluj-Napoca, Romania
*
Author to whom correspondence should be addressed.
Sustainability 2020, 12(22), 9707; https://doi.org/10.3390/su12229707
Received: 29 October 2020 / Accepted: 16 November 2020 / Published: 20 November 2020
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. View Full-Text
Keywords: convolutional neural network; image segmentation; neural architecture search; recurrent neural network; sustainable development convolutional neural network; image segmentation; neural architecture search; recurrent neural network; sustainable development
Show Figures

Figure 1

MDPI and ACS Style

Nistor, S.C.; Ileni, T.A.; Dărăbant, A.S. Automatic Development of Deep Learning Architectures for Image Segmentation. Sustainability 2020, 12, 9707. https://doi.org/10.3390/su12229707

AMA Style

Nistor SC, Ileni TA, Dărăbant AS. Automatic Development of Deep Learning Architectures for Image Segmentation. Sustainability. 2020; 12(22):9707. https://doi.org/10.3390/su12229707

Chicago/Turabian Style

Nistor, Sergiu Cosmin, Tudor Alexandru Ileni, and Adrian Sergiu Dărăbant. 2020. "Automatic Development of Deep Learning Architectures for Image Segmentation" Sustainability 12, no. 22: 9707. https://doi.org/10.3390/su12229707

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop