A Strong Baseline for Vehicle Re-Identification

TL;DR

This paper introduces a robust vehicle re-identification baseline that addresses domain gaps and employs advanced network modifications, achieving state-of-the-art results on multiple benchmarks without external data.

Contribution

The paper presents novel solutions including domain gap reduction, multi-head attention network modifications, and adaptive loss weighting for vehicle Re-ID.

Findings

Achieved 61.34% mAP on CityFlow testset without external data.

Outperformed previous methods with 87.1% mAP on Veri benchmark.

Proposed methods improve robustness across different views and conditions.

Abstract

Vehicle Re-Identification (Re-ID) aims to identify the same vehicle across different cameras, hence plays an important role in modern traffic management systems. The technical challenges require the algorithms must be robust in different views, resolution, occlusion and illumination conditions. In this paper, we first analyze the main factors hindering the Vehicle Re-ID performance. We then present our solutions, specifically targeting the dataset Track 2 of the 5th AI City Challenge, including (1) reducing the domain gap between real and synthetic data, (2) network modification by stacking multi heads with attention mechanism, (3) adaptive loss weight adjustment. Our method achieves 61.34% mAP on the private CityFlow testset without using external dataset or pseudo labeling, and outperforms all previous works at 87.1% mAP on the Veri benchmark. The code is available at https://github.com/cybercore-co-ltd/track2_aicity_2021.