Vehicle Re-Identification

36 papers with code • 12 benchmarks • 9 datasets

Vehicle re-identification is the task of identifying the same vehicle across multiple cameras.

( Image credit: A Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras )

Benchmarks

Add a Result

These leaderboards are used to track progress in Vehicle Re-Identification

Dataset	Best Model	Compare
VeRi-776	RPTM	See all
VehicleID Small	Recall@k Surrogate loss (ResNet-50)	See all
VehicleID Medium	Recall@k Surrogate loss (ResNet-50)	See all
VehicleID Large	Recall@k Surrogate loss (ResNet-50)	See all
VeRi	vehiclenet	See all
CityFlow	A Strong Baseline	See all
VeRi-Wild Small	ANet	See all
VeRi-Wild Medium	ANet	See all
VeRi-Wild Large	ANet	See all
VehicleID	VehicleNet	See all
VRAI test	Baseline Model	See all
VRAI test-dev	Baseline Model	See all

Show all 12 benchmarks

Collapse benchmarks

Libraries

Use these libraries to find Vehicle Re-Identification models and implementations

layumi/Person_reID_baseline_pytorch

2 papers

3,247

Datasets

Most implemented papers

Most implemented Social Latest No code

VehicleNet: Learning Robust Feature Representation for Vehicle Re-identification

layumi/Person_reID_baseline_pytorch • • 7 Aug 2020

This stage relaxes the full alignment between the training and testing domains, as it is agnostic to the target vehicle domain.

Paper
Code

TransReID: Transformer-based Object Re-Identification

heshuting555/TransReID • • ICCV 2021

Extracting robust feature representation is one of the key challenges in object re-identification (ReID).

Paper
Code

Simulating Content Consistent Vehicle Datasets with Attribute Descent

yorkeyao/VehicleX • • ECCV 2020

Between synthetic and real data, there is a two-level domain gap, i. e., content level and appearance level.

Paper
Code

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

heshuting555/AICITY2020_DMT_VehicleReID • • 22 Apr 2020

Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID.

Paper
Code

PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data

NVlabs/PAMTRI • • ICCV 2019

In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention.

Paper
Code

FastReID: A Pytorch Toolbox for General Instance Re-identification

JDAI-CV/fast-reid • • 4 Jun 2020

General Instance Re-identification is a very important task in the computer vision, which can be widely used in many practical applications, such as person/vehicle re-identification, face recognition, wildlife protection, commodity tracing, and snapshop, etc.. To meet the increasing application demand for general instance re-identification, we present FastReID as a widely used software system in JD AI Research.

Paper
Code

Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval

Andrew-Brown1/Smooth_AP • • ECCV 2020

Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods.

Paper
Code

Recall@k Surrogate Loss with Large Batches and Similarity Mixup

yash0307/RecallatK_surrogate • • CVPR 2022

This work focuses on learning deep visual representation models for retrieval by exploring the interplay between a new loss function, the batch size, and a new regularization approach.

Paper
Code