Multi-Domain Learning and Identity Mining for Vehicle Re-Identification

TL;DR

This paper presents a multi-domain learning approach combined with identity mining and ensemble techniques for vehicle re-identification, achieving third place in the AI City Challenge 2020.

Contribution

It introduces a novel multi-domain learning method and an identity mining technique for pseudo-label generation in vehicle ReID tasks.

Findings

Achieved 0.7322 mAP score in the competition

Outperformed k-means clustering for pseudo-labeling

Effective ensemble strategy improved results

Abstract

This paper introduces our solution for the Track2 in AI City Challenge 2020 (AICITY20). The Track2 is a vehicle re-identification (ReID) task with both the real-world data and synthetic data. Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID. At first, we propose a multi-domain learning method to joint the real-world and synthetic data to train the model. Then, we propose the Identity Mining method to automatically generate pseudo labels for a part of the testing data, which is better than the k-means clustering. The tracklet-level re-ranking strategy with weighted features is also used to post-process the results. Finally, with multiple-model ensemble, our method achieves 0.7322 in the mAP score which yields third place in the competition. The codes are available at https://github.com/heshuting555/AICITY2020_DMT_VehicleReID.