Dual-Dependency Attention Transformer for Fine-Grained Visual Classification
Sensors · 06.04.2024 · 24 (7) · 2337
DOI: 10.3390/s24072337 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 06.04.2024. Verfasst von Shiyan Cui und 1 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang 110016, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Visual transformers (ViTs) are widely used in various visual tasks, such as fine-grained visual classification (FGVC). However, the self-attention mechanism, which is the core module of visual transformers, leads to quadratic computational and memory complexity. The sparse-attention and local-attention approaches currently used by most researchers are not suitable for FGVC tasks. These tasks require dense feature extraction and global dependency modeling. To address this challenge, we propose a dual-dependency attention transformer model. It decouples global token interactions into two paths. The first is a position-dependency attention pathway based on the intersection of two types of grouped attention. The second is a semantic dependency attention pathway based on dynamic central aggregation. This approach enhances the high-quality semantic modeling of discriminative cues while reducing the computational cost to linear computational complexity. In addition, we develop discriminative enhancement strategies. These strategies increase the sensitivity of high-confidence discriminative cue tracking with a knowledge-based representation approach. Experiments on three datasets, NABIRDS, CUB, and DOGS, show that the method is suitable for fine-grained image classification. It finds a balance between computational cost and performance.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang 110016, China.
- Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China.
- Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China.
- University of Chinese Academy of Sciences, Beijing 100049, China.
ORCID-Profile: Bin Hui
Zitieren
APA
Cui, S., & Hui, B. (2024). Dual-Dependency Attention Transformer for Fine-Grained Visual Classification. Sensors, 24(7), 2337. https://doi.org/10.3390/s24072337
Vancouver
Cui S, Hui B. Dual-Dependency Attention Transformer for Fine-Grained Visual Classification. Sensors. 2024;24(7):2337. doi:10.3390/s24072337
BibTeX
@article{Cui2024,
author = {Cui, Shiyan and Hui, Bin},
title = {Dual-Dependency Attention Transformer for Fine-Grained Visual Classification},
journal = {Sensors},
year = {2024},
volume = {24},
number = {7},
pages = {2337},
doi = {10.3390/s24072337}
}
EUVIMED