Need help with IDE-baseline-Market-1501?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

233 Stars 95 Forks 122 Commits 1 Opened issues


ID-discriminative Embedding (IDE) for Person Re-identification

Services available


Need anything else?

Contributors list

# 32,380
114 commits
# 4,352
1 commit

Code for IDE baseline on Market-1501

============= This code was used for experiments with ID-discriminative Embedding (IDE) for Market-1501 dataset.

Thanks Liboyue, give us suggestions for improvement.

If you find this code useful in your research, please consider citing:

title={Person Re-identification: Past, Present and Future},
author={Zheng, Liang and Yang, Yi and Hauptmann, Alexander G},
journal={arXiv preprint arXiv:1610.02984},

@inproceedings{zheng2015scalable, title={Scalable Person Re-identification: A Benchmark}, author={Zheng, Liang and Shen, Liyue and Tian, Lu and Wang, Shengjin and Wang, Jingdong and Tian, Qi}, booktitle={Computer Vision, IEEE International Conference on}, year={2015} }

Requirements: Caffe

Requirements for

(see: Caffe installation instructions)


  1. Clone the IDE repository ```Shell

    Make sure to clone with --recursive

    git clone --recursive ```

  2. Build Caffe and matcaffe ```Shell cd $IDE_ROOT/caffe

    Now follow the Caffe installation instructions here:

    make -j8 && make matcaffe ```

  3. Download pre-computed models and Market-1501 dataset

    Please download the pre-trained imagenet models and put it in the "data/imagenet_models" folder.
    Please download Market-1501 dataset and unzip it in the "market_evaluation/dataset" folder. 

Training and testing IDE model

  1. Training ```Shell cd $IDEROOT  # train IDE on CaffeNet ./experiments/market/

    train IDE ResNet_50


    The IDE models are saved under: "out/market_train"

    If you encounter this problem: bash: ./experiments/market/ Permission denied

    Please execute: chmod 777 -R experiments/

  2. Feature Extraction ```Shell cd $IDEROOT/marketevaluation Run Matlab: extract_feature.m

    The IDE features are saved under: "market_evaluation/feat"

  3. Evaluation

    Run Matlab: baseline_evaluation_IDE.m


You can download our pre-trained IDE models and IDE features, and put them in the "output/markettrain" and "market_evaluation/feat" folder, respectively.

Using the models and features above, you can reproduce the results as follows:

|Methods |   [email protected] | mAP| | -------- | ----- | ---- | |IDECaffeNet + Euclidean | 59.53% | 32.85%| |IDECaffeNet + XQDA       | 62.00% | 37.55%| |IDECaffeNet + KISSME | 61.02% | 36.72%| |IDEResNet50 + Euclidean | 75.62% | 50.68%| |IDEResNet50 + XQDA | 76.01% | 52.98%| |IDEResNet_50 + KISSME | 77.52% | 53.88%|

If you add a dropout = 0.5 layer after pool5, you will get a better performance for ResNet_50:

|Methods |   [email protected] | mAP| | -------- | ----- | ---- | |IDEResNet50 + dropout(0.5) + Euclidean | 78.92% | 55.03%| |IDEResNet50 + dropout(0.5) + XQDA | 77.35% | 56.01%| |IDEResNet50 + dropout(0.5) + KISSME | 78.80% | 56.13%|

Contact us

If you have any questions about this code, please do not hesitate to contact us.

Zhun Zhong

Liang Zheng

Related Repos

Furthermore, you may check the following codes. 1. re-ranking 2. 2stream Network for reID 3. Person re-ID with GAN 4. Pedestrian Alignment Network 5. Random-Erasing

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.