An Empirical Study of Vehicle Re-Identification on the AI City Challenge

TL;DR

This paper presents a comprehensive vehicle re-identification solution for the AI City Challenge 2021, combining data augmentation, domain adaptation, post-processing, and model ensembling to achieve state-of-the-art results.

Contribution

It introduces a novel combination of training strategies, UDA techniques, post-processing, and model ensembling specifically tailored for vehicle ReID in complex scenarios.

Findings

Achieved 0.7445 mAP score, first place in the challenge.

Synthetic data and cropping improve feature discrimination.

Post-processing significantly boosts performance.

Abstract

This paper introduces our solution for the Track2 in AI City Challenge 2021 (AICITY21). The Track2 is a vehicle re-identification (ReID) task with both the real-world data and synthetic data. We mainly focus on four points, i.e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge. (1) Both cropping training data and using synthetic data can help the model learn more discriminative features. (2) Since there is a new scenario in the test set that dose not appear in the training set, UDA methods perform well in the challenge. (3) Post-processing techniques including re-ranking, image-to-track retrieval, inter-camera fusion, etc, significantly improve final performance. (4) We ensemble CNN-based models and transformer-based models which provide different representation diversity. With aforementioned techniques, our method finally achieves 0.7445 mAP score, yielding the first place in the competition. Codes are available at https://github.com/michuanhaohao/AICITY2021_Track2_DMT.