CVNet

KO | EN

gitlite — search

#python #hacktoberfest #react #ai #golang #android #rust #deep-learning #java #windows #cli #awesome-list #security #mcp

(★ 191)

Official PyTorch Implementation of Correlation Verification for Image Retrieval, CVPR 2022 (Oral Presentation)

파일 탐색기

최종 버전 다운로드 (.zip)

- CVNet_rerank_architecture.jpg
- __init__.py
- checkpoint.py
- config.py
- CVNet_tester.py
- transforms.py
- - conv4d.py
  - correlation.py
  - feature.py
  - geometry.py
- CVlearner.py
- CVNet_Rerank_model.py
- resnet.py
- __init__.py
- config_gnd.py
- dataset.py
- evaluate.py
- test_loader.py
- test_model.py
- test_utils.py
README.md
test.py

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Correlation Verification for Image Retrieval

> Official Pytorch Implementation of the paper "[**Correlation Verification for Image Retrieval**](https://openaccess.thecvf.com/content/CVPR2022/html/Lee_Correlation_Verification_for_Image_Retrieval_CVPR_2022_paper.html)" 
> _accept to **CVPR 2022** as an **oral presentation**_ 
> by Seongwon Lee, Hongje Seong, Suhyeon Lee, and Euntai Kim 
> Yonsei University
>

### Overall architecture

## ➡️ Guide to Our Code

### Data preparation
#### Download [ROxford5k and RParis6k](https://github.com/filipradenovic/revisitop). 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](https://drive.google.com/drive/folders/1gMbZ8JlTyPlH2-6HW5NHRe58LmKfJybx?usp=sharing).

### Testing
For ResNet-50 model, run the command
```bash
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
```bash
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](https://github.com/juhongm999/hsnet), [Revisiting Oxford and Paris](https://github.com/filipradenovic/revisitop) and [DELG-pytorch](https://github.com/feymanpriv/DELG). 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:
````BibTeX
@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}
}
````

CVNet

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

CVNet

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README