Unstructured Feature Decoupling for Vehicle Re-Identification pdf

• 2022.7 We release the code of UFDN.

pip install -r requirements.txt
(we use /torch 1.7.1 /torchvision 0.8.2 /timm 0.3.2 /cuda 11.0 / 16G or 32G V100 for training and evaluation.)

mkdir data

Download the vehicle datasets VehicleID, VeRi-776, VERIWILD. Then unzip them and rename them under the directory like

data
└── VeRi
    └── images ..
└── VehicleID
    └── images ..
└── VERI-WILD
    └── images ..

Datalist: VeRi-776

You need to download the ImageNet pretrained transformer model : Res50, Swin-tiny.

We utilize 1 GPU for training VeRi-776 Dataset

sh experiments/train_res50_UFDN_776.sh or train_swin_UFDN_776.sh

We utilize 1 GPU for training VehicleID Dataset

sh experiments/train_res50_UFDN_VehicleID.sh or train_swin_UFDN_VehicleID.sh

We have reproduced the performance to verify the reproducibility. The reproduced results may have a gap of about 0.1-0.2% with the numbers in the paper.