Saved in:
Bibliographic Details
Main Authors: Qiu, Mei, Christopher, Lauren Ann, Chien, Stanley, Li, Lingxi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.06297
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916476288499712
author Qiu, Mei
Christopher, Lauren Ann
Chien, Stanley
Li, Lingxi
author_facet Qiu, Mei
Christopher, Lauren Ann
Chien, Stanley
Li, Lingxi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06297
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Aspect Ratios with Patch-Mixup-ViT-based Vehicle ReID
Qiu, Mei
Christopher, Lauren Ann
Chien, Stanley
Li, Lingxi
Computer Vision and Pattern Recognition
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.
title Adaptive Aspect Ratios with Patch-Mixup-ViT-based Vehicle ReID
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.06297