yjhuasheng / darenet

(CVPR) Resource Aware Person Re-identification across Multiple Resolutions

Resource Aware Person Re-identification across Multiple Resolutions

This repository contains the code for paper "Resource Aware Person Re-identification across Multiple Resolutions" (CVPR 2018).

Citation

@inproceedings{wang2018resource,
  title={Resource Aware Person Re-identification across Multiple Resolutions},
  author={Wang, Yan and Wang, Lequn and You, Yurong and Zou, Xu and Chen, Vincent and Li, Serena and Huang, Gao and Hariharan, Bharath and Weinberger, Kilian Q},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={8042--8051},
  year={2018}
}

Usage

Dependencies

• Python3.6
• PyTorch(0.2.0)
• torchvision(0.2.0)
• Market1501 dataset
• MARS dataset
• CUHK03 dataset
• DukeMTMC-reID dataset

Usage

Training Dataset Preprocessing

Use the following command to preprocess the person re-id dataset.

python create_market_dataset.py --path <root_path_of_dataset>

Train

Use the following command to set up the training.

./train.sh <nettype> <GPU> <train_dataset_path> <checkpoint_name>

where <nettype> can be either dare_R or dare_D

Extract Features

Use the following command to load a trained model to generate features for each image (in .mat format).

./extract_features.sh <nettype> <GPU> <dataset_path> <dataset> <checkpoint_name> <feature_path> <gen_stage_features>

where <nettype> can be either dare_R or dare_D, <dataset> can be one of [MARS, Market1501, Duke, CUHK03], <feature_path> is the path to store extracted features. Toggle <gen_stage_features> to Ture to extract features from each stage.

Evaluation

Use person-re-ranking and MARS-evaluation official evaluation codes to evaluate the extracted features. Note we use mean rather than max to aggregate the image feature vectors for video sequences.

Resource-aware Person Re-ID Simulation

Use the following command to run simulations under resource-aware person re-ID scenarios. See here for more information.

./budgeted_stream/simulation.sh <dataset_path> <feature_path>

Pretrained Model

We provide several pretrained models listed below:

• Market1501 Res50
• Market1501 Dense201
• MARS Res50
• MARS Dense201
• CUHK Detected Res50
• CUHK Detected Dense201
• CUHK Labeled Res50
• CUHK Labeled Dense201
• Duke Res50
• Duke Dense201

License

MIT