Skip to content
프로젝트

msight-tech/research-xbm has 316 GitHub stars and 37 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-19 12:59 UTC. Last push 2022-12-27.

이 수치를 측정하는 방법

측정된 스타 증가

in 24h
0
in 7 days
기록 수집 중
in 15 days
기록 수집 중
in 1 month
기록 수집 중

서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.

소개

XBM: Cross-Batch Memory for Embedding Learning

학습

README.md

Original

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

  • Great Improvement: XBM can improve R@1 by 12~25% on three large-scale datasets

  • Memory Efficient: with less than 1GB for large-scale datasets

  • Elegant Algorithm: with an implementation that can be achieved in only several lines

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

[email protected]

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 [email protected].