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

2024-07-10 · Mei Qiu, Lauren Christopher, Lingxi Li

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.

📄 PDF Abstract BibTeX arXiv:2407.07842

Code (0)

등록된 구현이 없습니다.

Tasks

Vehicle Re-Identification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…

Scanner-Induced Domain Shifts Undermine the Robustness of Pathology Foundation Models

2026-01-07 · Erik Thiringer, Fredrik K. Gustafsson, Kajsa Ledesma Eriksson, Mattias Rantalainen arxiv

Pathology foundation models (PFMs) have become central to computational pathology, aiming to offer general encoders for feature extraction from whole-slide images (WSIs). Despite strong benchmark performance, PFM robustn…

Conditional Generative Models for High-Resolution Range Profiles: Capturing Geometry-Driven Trends in a Large-Scale Maritime Dataset

2026-02-09 · Edwyn Brient, Santiago Velasco-Forero, Rami Kassab arxiv

High-resolution range profiles (HRRPs) enable fast onboard processing for radar automatic target recognition, but their strong sensitivity to acquisition conditions limits robustness across operational scenarios. Conditi…

Scale free density and correlations fluctuations in the dynamics of large microbial ecosystems

2022-06-24 · Nahuel Zamponi, Tomas S. Grigera, Ewa Gudowska-Nowak, Dante R. Chialvo

Microorganisms self-organize in very large communities exhibiting complex fluctuations. Despite recent advances, still the mechanism by which these systems are able to exhibit large variability at the one hand and dynami…

Measuring Interventional Robustness in Reinforcement Learning

2022-09-19 · Katherine Avery, Jack Kenney, Pracheta Amaranath, Erica Cai 외

Recent work in reinforcement learning has focused on several characteristics of learned policies that go beyond maximizing reward. These properties include fairness, explainability, generalization, and robustness. In thi…

Fairness reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Vision-Based Driver Drowsiness Monitoring: Comparative Analysis of YOLOv5-v11 Models

2025-09-22 · Dilshara Herath, Chinthaka Abeyrathne, Prabhani Jayaweera arxiv

Driver drowsiness remains a critical factor in road accidents, accounting for thousands of fatalities and injuries each year. This paper presents a comprehensive evaluation of real-time, non-intrusive drowsiness detectio…

Autonomous Driving