# Data Augmentation Vision Transformer for Fine-grained Image Classification

arXiv: https://arxiv.org/abs/2211.12879 · HTML: https://mlsanity.com/paper/2211.12879/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 23 Nov 2022.

## Builds on (most cited first, 11 of 11)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [Vision Transformers are Robust Learners](https://mlsanity.com/paper/2105.07581/) (2021)
- [Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification](https://mlsanity.com/paper/2205.02151/) (2022)
- [Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization](https://mlsanity.com/paper/1909.11378/) (2019)
- [Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation](https://mlsanity.com/paper/1812.09912/) (2018)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)
- [Cross-Enhancement Transformer for Action Segmentation](https://mlsanity.com/paper/2205.09445/) (2022)
- [R2-Trans:Fine-Grained Visual Categorization with Redundancy Reduction](https://mlsanity.com/paper/2204.10095/) (2022)
- [Multi-View Active Fine-Grained Recognition](https://mlsanity.com/paper/2206.01153/) (2022)

## Built on by (most cited first, 2 of 2)

- [Which Tokens to Use? Investigating Token Reduction in Vision Transformers](https://mlsanity.com/paper/2308.04657/) (2023)
- [Agglomerative Token Clustering](https://mlsanity.com/paper/2409.11923/) (2024)

## Abstract (arXiv)

Recently, the vision transformer (ViT) has made breakthroughs in image recognition. Its self-attention mechanism (MSA) can extract discriminative labeling information of different pixel blocks to improve image classification accuracy. However, the classification marks in their deep layers tend to ignore local features between layers. In addition, the embedding layer will be fixed-size pixel blocks. Input network Inevitably introduces additional image noise. To this end, we study a data augmentation vision transformer (DAVT) based on data augmentation and proposes a data augmentation method for attention cropping, which uses attention weights as the guide to crop images and improve the ability of the network to learn critical features. Secondly, we also propose a hierarchical attention selection (HAS) method, which improves the ability of discriminative markers between levels of learning by filtering and fusing labels between levels. Experimental results show that the accuracy of this method on the two general datasets, CUB-200-2011, and Stanford Dogs, is better than the existing mainstream methods, and its accuracy is 1.4% and 1.6% higher than the original ViT, respectively