Exploring Self-Attention for Visual Intersection Classification
Journal of Advanced Computational Intelligence and Intelligent Informatics · 20.05.2023 · 27 (3) · 386-393
DOI: 10.20965/jaciii.2023.p0386 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advanced Computational Intelligence and Intelligent Informatics, online erschienen am 20.05.2023. Verfasst von Haruki Nakata und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Self-attention has recently emerged as a technique for capturing non-local contexts in robot vision. This study introduced a self-attention mechanism into an intersection recognition system to capture non-local contexts behind the scenes. This mechanism is effective in intersection classification because most parts of the local pattern (e.g., road edges, buildings, and sky) are similar; thus, the use of a non-local context (e.g., the angle between two diagonal corners around an intersection) would be effective. This study makes three major contributions to existing literature. First, we proposed a self-attention-based approach for intersection classification. Second, we integrated the self-attention-based classifier into a unified intersection classification framework to improve the overall recognition performance. Finally, experiments using the public KITTI dataset showed that the proposed self-attention-based system outperforms conventional recognition based on local patterns and recognition based on convolution operations.
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Nakata, H., Tanaka, K., & Takeda, K. (2023). Exploring Self-Attention for Visual Intersection Classification. Journal of Advanced Computational Intelligence and Intelligent Informatics, 27(3), 386-393. https://doi.org/10.20965/jaciii.2023.p0386
Vancouver
Nakata H, Tanaka K, Takeda K. Exploring Self-Attention for Visual Intersection Classification. Journal of Advanced Computational Intelligence and Intelligent Informatics. 2023;27(3):386-393. doi:10.20965/jaciii.2023.p0386
BibTeX
@article{Nakata2023,
author = {Nakata, Haruki and Tanaka, Kanji and Takeda, Koji},
title = {Exploring Self-Attention for Visual Intersection Classification},
journal = {Journal of Advanced Computational Intelligence and Intelligent Informatics},
year = {2023},
volume = {27},
number = {3},
pages = {386--393},
doi = {10.20965/jaciii.2023.p0386}
}
EUVIMED