Home

Awesome

License: CC BY-NC 4.0

Cross-Batch Memory for Embedding Learning (XBM)

Code for the CVPR 2020 paper (accepted as Oral) Cross-Batch Memory for Embedding Learning

XBM: A New SOTA Method for DML

<img src="misc/cvpr-mem-overview.png" width="95%" height="50%">

Installation

pip install -r requirements.txt
python setup.py develop build

Training and Evaluation

CUDA_VISIBLE_DEVICES=0 python3 tools/train_net.py --cfg configs/sample_config.yaml 

Contact

For any questions, please feel free to reach

github@malongtech.com

Citation

    If you use this method or this code in your research, please cite as:

    @inproceedings{wang2020xbm,
    title={Cross-Batch Memory for Embedding Learning},
    author={Wang, Xun and Zhang, Haozhi and Huang, Weilin and Scott, Matthew R},
    booktitle={CVPR},
    year={2020}
    }

    @inproceedings{wang2019multi,
    title={Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning},
    author={Wang, Xun and Han, Xintong and Huang, Weilin and Dong, Dengke and Scott, Matthew R},
    booktitle={CVPR},
    year={2019}
    }

License

XBM is CC-BY-NC 4.0 licensed, as found in the LICENSE file. It is released for academic research / non-commercial use only. If you wish to use for commercial purposes, please contact bd@malongtech.com.