Shared knowledge guidance and modal consistency learning for Visible-Infrared person re-identification
-
This project is based on AGW[1] (paper and official code) and DDAG[2] (paper and official code).
-
Usage of this code is free for research purposes only.
-
Our experimental environment: python3.8.10,torch1.9.0
-
Training
(1)Preparing the dataset(SYSU-MM01[3] (paper) and RegDB[4] (paper)). And follow AGW[1] to do data preprocessing.
(2)To begin training.(See the code and our paper for more details)
python train.py
- Testing.
(1)Preparing the dataset.(SYSU-MM01[3] (paper) and RegDB[4] (paper)).
(2)Downloading the parameter files trained in this paper.( Using to verify the effectiveness of the proposed method).Google Drive.
(3)To begin testing.(See the code for more details)
python test.py
- Reference
[1]Ye M, Shen J, Lin G, et al. Deep learning for person re-identification: A survey and outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
[2]Ye M, Shen J, J. Crandall D, et al. Dynamic dual-attentive aggregation learning for visible-infrared person re-identification[C]//Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVII 16. Springer International Publishing, 2020: 229-247.
[3]Wu A, Zheng W S, Yu H X, et al. RGB-infrared cross-modality person re-identification[C]//Proceedings of the IEEE international conference on computer vision. 2017: 5380-5389.
[4]Nguyen D T, Hong H G, Kim K W, et al. Person recognition system based on a combination of body images from visible light and thermal cameras[J]. Sensors, 2017, 17(3): 605.