CAGNet: A Multi-Scale Convolutional Attention Method for Glass Detection Based on Transformer
Mathematics · 26.09.2023 · 11 (19) · 4084
DOI: 10.3390/math11194084 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 26.09.2023. Verfasst von Xiaohang Hu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Electronics and Telecommunications Research Institute (ETRI), the Artificial Intelligence Convergence Innovation Human Resources Development.
Abstract (Originalsprache)
Glass plays a vital role in several fields, making its accurate detection crucial. Proper detection prevents misjudgments, reduces noise from reflections, and ensures optimal performance in other computer vision tasks. However, the prevalent usage of glass in daily applications poses unique challenges for computer vision. This study introduces a novel convolutional attention glass segmentation network (CAGNet) predicated on a transformer architecture customized for image glass detection. Based on the foundation of our prior study, CAGNet minimizes the number of training cycles and iterations, resulting in enhanced performance and efficiency. CAGNet is built upon the strategic design and integration of two types of convolutional attention mechanisms coupled with a transformer head applied for comprehensive feature analysis and fusion. To further augment segmentation precision, the network incorporates a custom edge-weighting scheme to optimize glass detection within images. Comparative studies and rigorous testing demonstrate that CAGNet outperforms several leading methodologies in glass detection, exhibiting robustness across a diverse range of conditions. Specifically, the IOU metric improves by 0.26% compared to that in our previous study and presents a 0.92% enhancement over those of other state-of-the-art methods.
Förderung
- the Electronics and Telecommunications Research Institute (ETRI)
- the Artificial Intelligence Convergence Innovation Human Resources Development
Zitieren
APA
Hu, X., Gao, R., Yang, S., & Cho, K. (2023). CAGNet: A Multi-Scale Convolutional Attention Method for Glass Detection Based on Transformer. Mathematics, 11(19), 4084. https://doi.org/10.3390/math11194084
Vancouver
Hu X, Gao R, Yang S, Cho K. CAGNet: A Multi-Scale Convolutional Attention Method for Glass Detection Based on Transformer. Mathematics. 2023;11(19):4084. doi:10.3390/math11194084
BibTeX
@article{Hu2023,
author = {Hu, Xiaohang and Gao, Rui and Yang, Seungjun and Cho, Kyungeun},
title = {CAGNet: A Multi-Scale Convolutional Attention Method for Glass Detection Based on Transformer},
journal = {Mathematics},
year = {2023},
volume = {11},
number = {19},
pages = {4084},
doi = {10.3390/math11194084}
}
EUVIMED