mlsanityData to 14 Oct 2026

Study on Aspect Ratio Variability toward Robustness of Vision Transformer-based Vehicle Re-identification

arXiv 2407.07842 ↗First posted 10 Jul 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Vision Transformers (ViTs) have excelled in vehicle re-identification (ReID) tasks. However, non-square aspect ratios of image or video input might significantly affect the re-identification performance. To address this issue, we propose a novel ViT-based ReID framework in this paper, which fuses models trained on a variety of aspect ratios. Our main contributions are threefold: (i) We analyze aspect ratio performance on VeRi-776 and VehicleID datasets, guiding input settings based on aspect ratios of original images. (ii) We introduce patch-wise mixup intra-image during ViT patchification (guided by spatial attention scores) and implement uneven stride for better object aspect ratio matching. (iii) We propose a dynamic feature fusing ReID network, enhancing model robustness. Our ReID method achieves a significantly improved mean Average Precision (mAP) of 91.0% compared to the the closest state-of-the-art (CAL) result of 80.9% on VehicleID dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 40 references that are in the map. First posted on arXiv 10 Jul 2024.

Builds on

21 of 40 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  7. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  8. 2021TransReID: Transformer-based Object Re-Identificationcited by 435
  9. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  10. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 229
  11. 2021Towards Robust Vision Transformercited by 137
  12. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
9 more
  1. 2016A Discriminatively Learned CNN Embedding for Person Re-identificationcited by 78
  2. 2016End-to-End Comparative Attention Networks for Person Re-identificationcited by 42
  3. 2020VehicleNet: Learning Robust Visual Representation for Vehicle Re-identificationcited by 42
  4. 2021Is 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 transformerscited by 16
  5. 2021Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systemscited by 8
  6. 2021Trends in Vehicle Re-identification Past, Present, and Future: A Comprehensive Reviewcited by 6
  7. 2022Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Taskcited by 6
  8. 2021An Empirical Study of Vehicle Re-Identification on the AI City Challengecited by 5
  9. 2019Improving Vehicle Re-Identification using CNN Latent Spaces: Metrics Comparison and Track-to-track Extensioncited by 2

Built on by

Not cited yet.