PyTorch implementation of Learning by Aligning (ICCV 2021)
This is an official PyTorch implementation of the paper "Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences", ICCV 2021.
For more details, visit our project site or see our paper.
Requirements
- Python 3.8
- PyTorch 1.7.1
- GPU memory >= 11GB
Getting started
First, clone our git repository.
git clone https://github.com/cvlab-yonsei/LbA.git
cd LbA
Docker
You can use docker pull sanghslee/ps:1.7.1-cuda11.0-cudnn8-runtime
Prepare datasets
- SYSU-MM01: download from this link.
- For SYSU-MM01, you need to preprocess the .jpg files into .npy files by running:
python utils/pre_preprocess_sysu.py --data_dir /path/to/SYSU-MM01
- Modify the dataset directory below accordingly.
- L63 of
train.py - L54 of
test.py
- L63 of
- For SYSU-MM01, you need to preprocess the .jpg files into .npy files by running:
Train
-
run
python train.py --method full -
Important:
- Performances reported during training does not reflect exact performances of your model. This is due to 1) evaluation protocols of the datasets and 2) random seed configurations.
- Make sure you seperately run
test.pyto obtain correct results to be reported in your paper.
- Performances reported during training does not reflect exact performances of your model. This is due to 1) evaluation protocols of the datasets and 2) random seed configurations.
Test
- run
python test.py --method full - The results should be around:
| dataset | method | mAP | rank-1 |
|---|---|---|---|
| SYSU-MM01 | baseline | 49.54 | 50.43 |
| SYSU-MM01 | full | 54.14 | 55.41 |
Pretrained weights
- Download [SYSU-MM01]
- The results should be:
| dataset | method | mAP | rank-1 |
|---|---|---|---|
| SYSU-MM01 | full | 55.22 | 56.31 |
Bibtex
@article{park2021learning,
title={Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences},
author={Park, Hyunjong and Lee, Sanghoon and Lee, Junghyup and Ham, Bumsub},
journal={arXiv preprint arXiv:2108.07422},
year={2021}
}
26 Dec 13, 2022
312 Dec 30, 2022
1 Jan 10, 2022
3 Feb 15, 2022
32 Jul 24, 2022
61 Dec 22, 2022
120 Dec 02, 2022
4.8k Jan 01, 2023
9 Nov 22, 2022
3.8k Jan 02, 2023
209 Dec 06, 2022
7 Dec 12, 2021
134 Nov 18, 2022
14 Oct 12, 2022
65 Dec 01, 2022
42 Jun 05, 2022
20 May 31, 2019
2 Nov 03, 2022
41 Dec 30, 2022
157 Aug 23, 2022