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

Martin Lukac, Kamila Abdiyeva, Michitaka Kameyama

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

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%.

本文言語English
ホスト出版物のタイトルInternational Conference on Information and Digital Technologies, IDT 2015
出版社Institute of Electrical and Electronics Engineers Inc.
ページ223-229
ページ数7
ISBN(電子版)9781467371858
DOI
出版ステータスPublished - 2015 8月 25
イベントInternational Conference on Information and Digital Technologies, IDT 2015 - Zilina, Slovakia
継続期間: 2015 7月 72015 7月 9

出版物シリーズ

名前International Conference on Information and Digital Technologies, IDT 2015

Other

OtherInternational Conference on Information and Digital Technologies, IDT 2015
国/地域Slovakia
CityZilina
Period15/7/715/7/9

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • 情報システム

フィンガープリント

「Evaluation of algorithm selection approach for semantic segmentation based on high-level information feedback」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル