# Adaptive Aspect Ratios with Patch-Mixup-ViT-based Vehicle ReID

arXiv: https://arxiv.org/abs/2411.06297 · HTML: https://mlsanity.com/paper/2411.06297/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 9 Nov 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution](https://mlsanity.com/paper/2307.06304/) (2023)
- [Towards Robust Vision Transformer](https://mlsanity.com/paper/2105.07926/) (2021)
- [GiT: Graph Interactive Transformer for Vehicle Re-identification](https://mlsanity.com/paper/2107.05475/) (2021)
- [VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification](https://mlsanity.com/paper/2004.06305/) (2020)
- [Is the aspect ratio of cells important in deep learning? A robust comparison of deep learning methods for multi-scale cytopathology cell image classification: from convolutional neural networks to visual transformers](https://mlsanity.com/paper/2105.07402/) (2021)
- [A Comprehensive Survey on Deep-Learning-based Vehicle Re-Identification: Models, Data Sets and Challenges](https://mlsanity.com/paper/2401.10643/) (2024)
- [Trends in Vehicle Re-identification Past, Present, and Future: A Comprehensive Review](https://mlsanity.com/paper/2102.09744/) (2021)
- [Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Task](https://mlsanity.com/paper/2204.02181/) (2022)
- [An Empirical Study of Vehicle Re-Identification on the AI City Challenge](https://mlsanity.com/paper/2105.09701/) (2021)
- [Improving Vehicle Re-Identification using CNN Latent Spaces: Metrics Comparison and Track-to-track Extension](https://mlsanity.com/paper/1910.09458/) (2019)

## Built on by (most cited first, 1 of 1)

- [What Makes You Unique? Attribute Prompt Composition for Object Re-Identification](https://mlsanity.com/paper/2509.18715/) (2025)

## Abstract (arXiv)

Vision Transformers (ViTs) have shown exceptional performance in vehicle re-identification (ReID) tasks. However, non-square aspect ratios of image or video inputs can negatively impact re-identification accuracy. To address this challenge, we propose a novel, human perception driven, and general ViT-based ReID framework that fuses models trained on various aspect ratios. Our key contributions are threefold: (i) We analyze the impact of aspect ratios on performance using the VeRi-776 and VehicleID datasets, providing guidance for input settings based on the distribution of original image aspect ratios. (ii) We introduce patch-wise mixup strategy during ViT patchification (guided by spatial attention scores) and implement uneven stride for better alignment with object aspect ratios. (iii) We propose a dynamic feature fusion ReID network to enhance model robustness. Our method outperforms state-of-the-art transformer-based approaches on both datasets, with only a minimal increase in inference time per image.