IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v12y2020i22p9707-d448572.html
   My bibliography  Save this article

Automatic Development of Deep Learning Architectures for Image Segmentation

Author

Listed:
  • 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)

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.

Suggested Citation

  • Sergiu Cosmin Nistor & Tudor Alexandru Ileni & Adrian Sergiu Dărăbant, 2020. "Automatic Development of Deep Learning Architectures for Image Segmentation," Sustainability, MDPI, vol. 12(22), pages 1-18, November.
    • Handle: RePEc:gam:jsusta:v:12:y:2020:i:22:p:9707-:d:448572
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/12/22/9707/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2071-1050/12/22/9707/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Chao Li & Hong Zhou, 2018. "Enhancing the Efficiency of Massive Online Learning by Integrating Intelligent Analysis into MOOCs with an Application to Education of Sustainability," Sustainability, MDPI, vol. 10(2), pages 1-16, February.
    2. Pei-Jarn Chen & Szu-Yueh Yang & Chung-Sheng Wang & Muslikhin Muslikhin & Ming-Shyan Wang, 2020. "Development of a Chinese Chess Robotic System for the Elderly Using Convolutional Neural Networks," Sustainability, MDPI, vol. 12(10), pages 1-20, May.
    3. Kai CHEN & Roxana STEGEREAN & Razvan-Liviu NISTOR, 2017. "A Modern Management Approach In Internet Era," Proceedings of the INTERNATIONAL MANAGEMENT CONFERENCE, Faculty of Management, Academy of Economic Studies, Bucharest, Romania, vol. 11(1), pages 918-927, November.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Tomáš Tichý & David Švorc & Miroslav Růžička & Zuzana Bělinová, 2021. "Thermal Feature Detection of Vehicle Categories in the Urban Area," Sustainability, MDPI, vol. 13(12), pages 1-13, June.
    2. David Švorc & Tomáš Tichý & Miroslav Růžička & Petr Ivasienko, 2023. "Use of One-Stage Detector and Feature Detector in Infrared Video on Transport Infrastructure and Tunnels," Sustainability, MDPI, vol. 15(3), pages 1-21, January.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Jesús Maya & Juan F. Luesia & Javier Pérez-Padilla, 2021. "The Relationship between Learning Styles and Academic Performance: Consistency among Multiple Assessment Methods in Psychology and Education Students," Sustainability, MDPI, vol. 13(6), pages 1-18, March.
    2. Bernardo Tabuenca & Marco Kalz & Ansje Löhr, 2019. "Massive Open Online Education for Environmental Activism: The Worldwide Problem of Marine Litter," Sustainability, MDPI, vol. 11(10), pages 1-16, May.
    3. Serdar Türkeli & Martine Schophuizen, 2019. "Decomposing the Complexity of Value: Integration of Digital Transformation of Education with Circular Economy Transition," Social Sciences, MDPI, vol. 8(8), pages 1-22, August.
    4. Chih-Shiang (Mike) Wu & Tung-Jung (David) Sung, 2021. "Applying Values-Led Communication Design to Engage Stakeholders in Developing Dementia-Friendly Visitor Destinations," Sustainability, MDPI, vol. 13(8), pages 1-25, April.
    5. Eva Gómez-Llanos & Pablo Durán-Barroso, 2020. "Learning Design Decisions in Massive Open Online Courses (MOOC) Applied to Higher Education in Civil-Engineering Topics," Sustainability, MDPI, vol. 12(20), pages 1-13, October.
    6. Ling Wang & Gongliang Hu & Tiehua Zhou, 2018. "Semantic Analysis of Learners’ Emotional Tendencies on Online MOOC Education," Sustainability, MDPI, vol. 10(6), pages 1-19, June.
    7. Chiou-Jye Huang & Ping-Huan Kuo, 2018. "A Short-Term Wind Speed Forecasting Model by Using Artificial Neural Networks with Stochastic Optimization for Renewable Energy Systems," Energies, MDPI, vol. 11(10), pages 1-20, October.
    8. Muhammad Imran & Saman Hina & Mirza Mahmood Baig, 2022. "Analysis of Learner’s Sentiments to Evaluate Sustainability of Online Education System during COVID-19 Pandemic," Sustainability, MDPI, vol. 14(8), pages 1-18, April.
    9. Cecilia Temilola Olugbara & Moeketsi Letseka & Oludayo O. Olugbara, 2021. "Multiple Correspondence Analysis of Factors Influencing Student Acceptance of Massive Open Online Courses," Sustainability, MDPI, vol. 13(23), pages 1-21, December.
    10. Martín Bustamante-León & Paúl Herrera & Luis Domínguez-Granda & Tammy Schellens & Peter L. M. Goethals & Otilia Alejandro & Martin Valcke, 2022. "Toward a More Personalized MOOC: Data Analysis to Identify Drinking Water Production Operators’ Learning Characteristics—An Ecuador Case," Sustainability, MDPI, vol. 14(21), pages 1-31, November.
    11. María Consuelo Sáiz-Manzanares & Raúl Marticorena-Sánchez & Javier Ochoa-Orihuel, 2020. "Effectiveness of Using Voice Assistants in Learning: A Study at the Time of COVID-19," IJERPH, MDPI, vol. 17(15), pages 1-20, August.
    12. Jorge Morato & Sonia Sanchez-Cuadrado & Ana Iglesias & Adrián Campillo & Carmen Fernández-Panadero, 2021. "Sustainable Technologies for Older Adults," Sustainability, MDPI, vol. 13(15), pages 1-35, July.
    13. Chi-Cheng Chang & Chin-Guo Kuo & Yu-Hsuan Chang, 2018. "An Assessment Tool Predicts Learning Effectiveness for Project-Based Learning in Enhancing Education of Sustainability," Sustainability, MDPI, vol. 10(10), pages 1-15, October.
    14. María José Sosa-Díaz & María Rosa Fernández-Sánchez, 2020. "Massive Open Online Courses (MOOC) within the Framework of International Developmental Cooperation as a Strategy to Achieve Sustainable Development Goals," Sustainability, MDPI, vol. 12(23), pages 1-23, December.
    15. Walter Leal Filho & Elizabeth Price & Tony Wall & Chris Shiel & Ulisses M. Azeiteiro & Mark Mifsud & Luciana Brandli & Carla Sofia Farinha & Sandra Caeiro & Amanda Lange Salvia & Claudio Ruy Vasconcel, 2021. "COVID-19: the impact of a global crisis on sustainable development teaching," Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, Springer, vol. 23(8), pages 11257-11278, August.
    16. Ishteyaaq Ahmad & Sonal Sharma & Rajesh Singh & Anita Gehlot & Neeraj Priyadarshi & Bhekisipho Twala, 2022. "MOOC 5.0: A Roadmap to the Future of Learning," Sustainability, MDPI, vol. 14(18), pages 1-17, September.
    17. Ping-Huan Kuo & Chiou-Jye Huang, 2018. "An Electricity Price Forecasting Model by Hybrid Structured Deep Neural Networks," Sustainability, MDPI, vol. 10(4), pages 1-17, April.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:12:y:2020:i:22:p:9707-:d:448572. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.