Skip to Content
You are currently on the new version of our website. Access the old version .
ProcessesProcesses
  • Article
  • Open Access

30 January 2026

21 Pages

Token Injection Transformer for Enhanced Fine-Grained Recognition

,
,
,
,
,
and
1
College of Electronic and Electrical Engineering, Henan Normal University, Xinxiang 453007, China
2
Institute of Physics, Henan Academy of Sciences, Zhengzhou 450046, China
3
Henan Academy of Sciences, Zhengzhou 450046, China
4
Center for Precision Medicine, Sun Yat-sen University, Guangzhou 510275, China

Abstract

Fine-Grained Visual Classification (FGVC) involves distinguishing highly similar subordinate categories within the same basic-level class, presenting significant challenges due to subtle inter-class variations and substantial intra-class diversity. While Vision Transformer (ViT)-based approaches have demonstrated potential in this domain, they remain limited by two key issues: (1) the progressive loss of gradient-based edge and texture signals during hierarchical token aggregation and (2) insufficient extraction of discriminative fine-grained features. To overcome these limitations, we propose a Gradient-Aware Token Injection Transformer, a novel framework that explicitly incorporates gradient magnitude and orientation into token embeddings. This multi-modal feature fusion mechanism enhances the model’s capacity to preserve and leverage critical fine-grained visual cues. Extensive experiments on four standard FGVC benchmarks demonstrate the superiority of our approach, achieving 92.9% top-1 accuracy on CUB-200-2011, 90.5% on iNaturalist 2018, 93.2% on NABirds, and 95.3% on Stanford Cars, thereby validating its effectiveness and robustness.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.