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

TL;DR

This paper introduces a novel ViT-based vehicle ReID framework that adaptively handles non-square aspect ratios through patch-wise mixup, uneven stride, and dynamic feature fusion, improving accuracy with minimal inference overhead.

Contribution

The paper proposes a new ViT-based vehicle ReID method that adaptively manages aspect ratios, combining patch-wise mixup, uneven stride, and dynamic feature fusion for improved robustness.

Findings

Outperforms state-of-the-art transformer-based methods on VeRi-776 and VehicleID datasets.

Provides analysis of aspect ratio impacts on ReID performance.

Achieves higher accuracy with minimal increase in inference time.

Abstract

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.