English

Feature Fusion Vision Transformer for Fine-Grained Visual Categorization

Computer Vision and Pattern Recognition 2022-03-02 v3

Abstract

The core for tackling the fine-grained visual categorization (FGVC) is to learn subtle yet discriminative features. Most previous works achieve this by explicitly selecting the discriminative parts or integrating the attention mechanism via CNN-based approaches.However, these methods enhance the computational complexity and make the modeldominated by the regions containing the most of the objects. Recently, vision trans-former (ViT) has achieved SOTA performance on general image recognition tasks. Theself-attention mechanism aggregates and weights the information from all patches to the classification token, making it perfectly suitable for FGVC. Nonetheless, the classifi-cation token in the deep layer pays more attention to the global information, lacking the local and low-level features that are essential for FGVC. In this work, we proposea novel pure transformer-based framework Feature Fusion Vision Transformer (FFVT)where we aggregate the important tokens from each transformer layer to compensate thelocal, low-level and middle-level information. We design a novel token selection mod-ule called mutual attention weight selection (MAWS) to guide the network effectively and efficiently towards selecting discriminative tokens without introducing extra param-eters. We verify the effectiveness of FFVT on three benchmarks where FFVT achieves the state-of-the-art performance.

Keywords

Cite

@article{arxiv.2107.02341,
  title  = {Feature Fusion Vision Transformer for Fine-Grained Visual Categorization},
  author = {Jun Wang and Xiaohan Yu and Yongsheng Gao},
  journal= {arXiv preprint arXiv:2107.02341},
  year   = {2022}
}

Comments

This paper was accepted by BMVC2021

R2 v1 2026-06-24T03:54:59.556Z