Back to Search
Start Over
Dual-Dependency Attention Transformer for Fine-Grained Visual Classification.
- Source :
-
Sensors (14248220) . Apr2024, Vol. 24 Issue 7, p2337. 23p. - Publication Year :
- 2024
-
Abstract
- 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. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 14248220
- Volume :
- 24
- Issue :
- 7
- Database :
- Academic Search Index
- Journal :
- Sensors (14248220)
- Publication Type :
- Academic Journal
- Accession number :
- 176594705
- Full Text :
- https://doi.org/10.3390/s24072337