Code for the CVPR 2019 paper Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
| Rank@K | 1 | 2 | 4 | 8 | 16 | 32 |
|---|---|---|---|---|---|---|
| Clustering64 | 48.2 | 61.4 | 71.8 | 81.9 | - | - |
| ProxyNCA64 | 49.2 | 61.9 | 67.9 | 72.4 | - | - |
| Smart Mining64 | 49.8 | 62.3 | 74.1 | 83.3 | - | |
| Our MS-Loss64 | 57.4 | 69.8 | 80.0 | 87.8 | 93.2 | 96.4 |
| HTL512 | 57.1 | 68.8 | 78.7 | 86.5 | 92.5 | 95.5 |
| ABIER512 | 57.5 | 68.7 | 78.3 | 86.2 | 91.9 | 95.5 |
| Our MS-Loss512 | 65.7 | 77.0 | 86.3 | 91.2 | 95.0 | 97.3 |
The following script will prepare the CUB dataset for training by downloading to the ./resource/datasets/ folder; which will then build the data list (train.txt test.txt):
./scripts/prepare_cub.shDownload the imagenet pretrained model of bninception and put it in the folder: ~/.torch/models/.
pip install -r requirements.txt
python setup.py develop build./scripts/run_cub.shTrained models will be saved in the ./output/ folder if using the default config.
Best recall@1 higher than 66 (65.7 in the paper).
For any questions, please feel free to reach
github@malongtech.com
If you use this method or this code in your research, please cite as:
@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={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={5022--5030},
year={2019}
}
MS-Loss 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 sales@malongtech.com.