Unsupervised Domain Adaptive Re-Identification

Implementation of the paper Unsupervised Domain Adaptive Re-Identification: Theory and Practice.

The selftraining scheme proposed in the paper is simple yet effective.

Running the experiments

Step 1: Train on source dataset

Run source_train.py via

python source_train.py \
    --dataset <name_of_source_dataset>\
    --resume <dir_of_source_trained_model>\
    --data_dir <dir_of_source_data>\
    --logs_dir <dir_to_save_source_trained_model>

To replicate the results in the paper, you can download pre-trained models on Market1501 from GoogleDrive and on DukeMTMC from GoogleDrive. Our models are trained with PyTorch 0.3.

Step 2: Run self-training

python selftraining.py \
    --src_dataset <name_of_source_dataset>\
    --tgt_dataset <name_of_target_dataset>\
    --resume <dir_of_source_trained_model>\
    --data_dir <dir_of_source_target_data>\
    --logs_dir <dir_to_save_model_after_adaptation>

Other code

dw_example.ipynb is the file for replicating Figure 6 in the paper.

Results

Step 1: After training on source dataset

Step 2: After adaptation

FAQ

If you found difficulty in reproducing our reported results, please check the number of GPUs in your experiments. This may be caused by the un-sync BN layer implementation of PyTorch. Below we provide some training logs with the setting Duke --> Market, for helping you check your experiment settings.

With 1 GPU

OneDrive Download Link

With 2 GPU

OneDrive Download Link

Acknowledgement

Our code is based on open-reid.