Create pret-benchmark

[Zengxianxian727]

Multi-Similarity Loss for Deep Metric Learning (MS-Loss)

This is the unofficial code with Paddlepaddle for the CVPR 2019 paper Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning

And the official code is here

Initial Paddlepaddle 1.8.x

pip install paddlepaddle-gpu

Prepare the data and the pretrained model

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.sh

Download the imagenet pretrained model of
bninception and put it in the folder. And then we should use it to generate the Paddlepaddle pretrained model.

python ./pretrained_model/pytorch2paddle.py

Installation

python setup.py develop build

Train and Test on CUB200-2011 with MS-Loss

./scripts/run_cub.sh

Trained models will be saved in the ./output/ folder if using the default config.

Best recall@1 is 65.1 (65.7 in the paper).

Contact

For any questions, please feel free to reach

zengxianxian727@foxmail.com

Citation

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}
}

License

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 zengxianxian727@foxmail.com

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[Zengxianxian727]

research-ms-loss-paddle.zip