Home

Awesome

Correlation Verification for Image Retrieval

Official Pytorch Implementation of the paper "Correlation Verification for Image Retrieval"<br> accept to CVPR 2022 as an oral presentation <br> by Seongwon Lee, Hongje Seong, Suhyeon Lee, and Euntai Kim<br> Yonsei University

Overall architecture

<p align="middle"> <img src="assets/CVNet_rerank_architecture.jpg"> </p>

➡️ Guide to Our Code

Data preparation

Download ROxford5k and RParis6k. Unzip the files and make the directory structures as follows.

revisitiop
 └ data
   └ datasets
     └ roxford5k
       └ gnd_roxford5k.pkl
       └ jpg
         └ ...
     └ rparis6k
       └ gnd_rparis6k.pkl
       └ jpg
         └ ...

Pretrained models

You can download our pretrained models from Google Drive.

Testing

For ResNet-50 model, run the command

python test.py MODEL.DEPTH 50 TEST.WEIGHTS <path-to-R50-pretrained-model> TEST.DATA_DIR <path_to_revisitop>/data/datasets

and for ResNet-101 model, run the command

python test.py MODEL.DEPTH 101 TEST.WEIGHTS <path-to-R101-pretrained-model> TEST.DATA_DIR <path_to_revisitop>/data/datasets

🙏 Acknowledgments

Our pytorch implementation is derived from HSNet, Revisiting Oxford and Paris and DELG-pytorch. We thank for these great works and repos.

✏️ Citation

If you find our paper useful in your research, please cite us using the following entry:

@InProceedings{lee2022cvnet, 
    author    = {Lee, Seongwon and Seong, Hongje and Lee, Suhyeon and Kim, Euntai},
    title     = {Correlation Verification for Image Retrieval},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {5374-5384}
}