{Sam Kwong Zhengguo Li Mingliang Zhou Zhenzhe Hechen Yueting Huang}

Abstract

Fine-grained visual classification (FGVC) is a challenging task characterized by interclass similarity and intraclass diversity and has broad application prospects. Recently, several methods have adopted the vision Transformer (ViT) in FGVC tasks since the data specificity of the multihead self-attention (MSA) mechanism in ViT is beneficial for extracting discriminative feature representations. However, these works focus on integrating feature dependencies at a high level, which leads to the model being easily disturbed by low-level background information. To address this issue, we propose a fine-grained attention-locating vision Transformer (FAL-ViT) and an attention selection module (ASM). First, FAL-ViT contains a two-stage framework to identify crucial regions effectively within images and enhance features by strategically reusing parameters. Second, the ASM accurately locates important target regions via the natural scores of the MSA, extracting finer low-level features to offer more comprehensive information through position mapping. Extensive experiments on public datasets demonstrate that FAL-ViT outperforms the other methods in terms of performance, confirming the effectiveness of our proposed methods. The source code is available at https://github.com/Yueting-Huang/FAL-ViT.