PKU-ICST-MIPL / C2R_CVPR2024

Introduction

This is the source code of our CVPR 2024 paper "Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification". Please cite the following paper if you use our code.

Zhenyu Cui, Jiahuan Zhou, Xun Wang, Manyu Zhu and Yuxin Peng, "Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification", 37th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle WA, USA, June 17 - 21, 2024.

Dependencies

• Python 3.7

• PyTorch 1.13.1

Data Preparation

• Please follow PatchKD to download datasets and unzip them to your data path.

Environment Preparation

• Please follow PatchKD to prepare the execution environment.

Usage

• Start training by executing the following commands.

1. For Order-1:

   • Train: CUDA_VISIBLE_DEVICES=0 python train1.py
   • Test: CUDA_VISIBLE_DEVICES=0 python test1.py

2. For Order-2:

   • Train: CUDA_VISIBLE_DEVICES=1 python train2.py
   • Test: CUDA_VISIBLE_DEVICES=1 python test2.py

For any questions, feel free to contact us ([e-mail]).

Welcome to our Laboratory Homepage for more information about our papers, source codes, and datasets.

Acknowledgement

Our code is based on the PyTorch implementation of PatchKD.