Evaluation of algorithm selection approach for semantic segmentation based on high-level information feedback

Martin Lukac, Kamila Abdiyeva, Michitaka Kameyama

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    In this paper we discuss certain theoretical properties of the algorithm selection approach to the problem of semantic segmentation in computer vision. We show that an algorithm's score depends on final task. Thus to properly evaluate an algorithm and to determine its suitability, precise score value obtained on well formulated tasks can be used only. When an algorithm suitability is well known, the algorithm can be efficiently used for a task by applying it in the most favorable environmental conditions determined during the evaluation. However, high quality algorithm selection is possible only if each algorithm suitability is well known because only then the algorithm selection result can improve the best possible result given by a single algorithm. The task dependent evaluation is demonstrated on segmentation and object recognition. Additionally, we also discuss the importance of high level symbolic knowledge in the selection process. The importance of this symbolic hypothesis is demonstrated on a set of learning experiments with both a Bayesian Network and SVM. We show that task dependent evaluation is required to allow efficient algorithm selection. Also by studying symbolic preference of algorithms for semantic segmentation we show that algorithm selection accuracy can be improved by 10 to 15%.

    Original languageEnglish
    Title of host publicationInternational Conference on Information and Digital Technologies, IDT 2015
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages223-229
    Number of pages7
    ISBN (Print)9781467371858
    DOIs
    Publication statusPublished - Aug 25 2015
    EventInternational Conference on Information and Digital Technologies, IDT 2015 - Zilina, Slovakia
    Duration: Jul 7 2015Jul 9 2015

    Other

    OtherInternational Conference on Information and Digital Technologies, IDT 2015
    CountrySlovakia
    CityZilina
    Period7/7/157/9/15

    Fingerprint

    Semantics
    Feedback
    Object recognition
    Bayesian networks
    Computer vision

    Keywords

    • Algorithm Selection
    • Machine Learning
    • Semantic Segmentation

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Science Applications
    • Information Systems

    Cite this

    Lukac, M., Abdiyeva, K., & Kameyama, M. (2015). Evaluation of algorithm selection approach for semantic segmentation based on high-level information feedback. In International Conference on Information and Digital Technologies, IDT 2015 (pp. 223-229). [7222974] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DT.2015.7222974

    Evaluation of algorithm selection approach for semantic segmentation based on high-level information feedback. / Lukac, Martin; Abdiyeva, Kamila; Kameyama, Michitaka.

    International Conference on Information and Digital Technologies, IDT 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 223-229 7222974.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Lukac, M, Abdiyeva, K & Kameyama, M 2015, Evaluation of algorithm selection approach for semantic segmentation based on high-level information feedback. in International Conference on Information and Digital Technologies, IDT 2015., 7222974, Institute of Electrical and Electronics Engineers Inc., pp. 223-229, International Conference on Information and Digital Technologies, IDT 2015, Zilina, Slovakia, 7/7/15. https://doi.org/10.1109/DT.2015.7222974
    Lukac M, Abdiyeva K, Kameyama M. Evaluation of algorithm selection approach for semantic segmentation based on high-level information feedback. In International Conference on Information and Digital Technologies, IDT 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 223-229. 7222974 https://doi.org/10.1109/DT.2015.7222974
    Lukac, Martin ; Abdiyeva, Kamila ; Kameyama, Michitaka. / Evaluation of algorithm selection approach for semantic segmentation based on high-level information feedback. International Conference on Information and Digital Technologies, IDT 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 223-229
    @inproceedings{2b5435991e774289aea3ff901a5e4af6,
    title = "Evaluation of algorithm selection approach for semantic segmentation based on high-level information feedback",
    abstract = "In this paper we discuss certain theoretical properties of the algorithm selection approach to the problem of semantic segmentation in computer vision. We show that an algorithm's score depends on final task. Thus to properly evaluate an algorithm and to determine its suitability, precise score value obtained on well formulated tasks can be used only. When an algorithm suitability is well known, the algorithm can be efficiently used for a task by applying it in the most favorable environmental conditions determined during the evaluation. However, high quality algorithm selection is possible only if each algorithm suitability is well known because only then the algorithm selection result can improve the best possible result given by a single algorithm. The task dependent evaluation is demonstrated on segmentation and object recognition. Additionally, we also discuss the importance of high level symbolic knowledge in the selection process. The importance of this symbolic hypothesis is demonstrated on a set of learning experiments with both a Bayesian Network and SVM. We show that task dependent evaluation is required to allow efficient algorithm selection. Also by studying symbolic preference of algorithms for semantic segmentation we show that algorithm selection accuracy can be improved by 10 to 15{\%}.",
    keywords = "Algorithm Selection, Machine Learning, Semantic Segmentation",
    author = "Martin Lukac and Kamila Abdiyeva and Michitaka Kameyama",
    year = "2015",
    month = "8",
    day = "25",
    doi = "10.1109/DT.2015.7222974",
    language = "English",
    isbn = "9781467371858",
    pages = "223--229",
    booktitle = "International Conference on Information and Digital Technologies, IDT 2015",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    TY - GEN

    T1 - Evaluation of algorithm selection approach for semantic segmentation based on high-level information feedback

    AU - Lukac, Martin

    AU - Abdiyeva, Kamila

    AU - Kameyama, Michitaka

    PY - 2015/8/25

    Y1 - 2015/8/25

    N2 - In this paper we discuss certain theoretical properties of the algorithm selection approach to the problem of semantic segmentation in computer vision. We show that an algorithm's score depends on final task. Thus to properly evaluate an algorithm and to determine its suitability, precise score value obtained on well formulated tasks can be used only. When an algorithm suitability is well known, the algorithm can be efficiently used for a task by applying it in the most favorable environmental conditions determined during the evaluation. However, high quality algorithm selection is possible only if each algorithm suitability is well known because only then the algorithm selection result can improve the best possible result given by a single algorithm. The task dependent evaluation is demonstrated on segmentation and object recognition. Additionally, we also discuss the importance of high level symbolic knowledge in the selection process. The importance of this symbolic hypothesis is demonstrated on a set of learning experiments with both a Bayesian Network and SVM. We show that task dependent evaluation is required to allow efficient algorithm selection. Also by studying symbolic preference of algorithms for semantic segmentation we show that algorithm selection accuracy can be improved by 10 to 15%.

    AB - In this paper we discuss certain theoretical properties of the algorithm selection approach to the problem of semantic segmentation in computer vision. We show that an algorithm's score depends on final task. Thus to properly evaluate an algorithm and to determine its suitability, precise score value obtained on well formulated tasks can be used only. When an algorithm suitability is well known, the algorithm can be efficiently used for a task by applying it in the most favorable environmental conditions determined during the evaluation. However, high quality algorithm selection is possible only if each algorithm suitability is well known because only then the algorithm selection result can improve the best possible result given by a single algorithm. The task dependent evaluation is demonstrated on segmentation and object recognition. Additionally, we also discuss the importance of high level symbolic knowledge in the selection process. The importance of this symbolic hypothesis is demonstrated on a set of learning experiments with both a Bayesian Network and SVM. We show that task dependent evaluation is required to allow efficient algorithm selection. Also by studying symbolic preference of algorithms for semantic segmentation we show that algorithm selection accuracy can be improved by 10 to 15%.

    KW - Algorithm Selection

    KW - Machine Learning

    KW - Semantic Segmentation

    UR - http://www.scopus.com/inward/record.url?scp=84954349181&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84954349181&partnerID=8YFLogxK

    U2 - 10.1109/DT.2015.7222974

    DO - 10.1109/DT.2015.7222974

    M3 - Conference contribution

    AN - SCOPUS:84954349181

    SN - 9781467371858

    SP - 223

    EP - 229

    BT - International Conference on Information and Digital Technologies, IDT 2015

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -