https://github.com/zjcv/dcl
[CVPR 2019] Destruction and Construction Learning for Fine-grained Image Recognition
https://github.com/zjcv/dcl
dcl python pytorch zcls
Last synced: about 1 month ago
JSON representation
[CVPR 2019] Destruction and Construction Learning for Fine-grained Image Recognition
- Host: GitHub
- URL: https://github.com/zjcv/dcl
- Owner: ZJCV
- License: apache-2.0
- Created: 2021-10-22T12:54:57.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2021-10-28T11:21:17.000Z (over 4 years ago)
- Last Synced: 2025-03-04T19:02:14.481Z (over 1 year ago)
- Topics: dcl, python, pytorch, zcls
- Language: Python
- Homepage:
- Size: 159 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
«DCL» re-implements the paper Destruction and Construction Learning for Fine-Grained Image Recognition
More training statistics can see:
* [Details](./docs/readme.md)
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Background](#background)
- [Installation](#installation)
- [Usage](#usage)
- [Maintainers](#maintainers)
- [Thanks](#thanks)
- [Contributing](#contributing)
- [License](#license)
## Background
Differ with other attention-based or part-based fine-classification methods, DCL adds an Destruction Module (`Region Confusion Mechanism` and `Adversarial Learning Network`) and Construction Module (`Region Align Network`) in training, and only use backbone network in infer. Improve the accuracy of the model without affecting the reasoning speed.
Current project implementation is based on [ JDAI-CV/DCL](https://github.com/JDAI-CV/DCL).
## Installation
```
$ pip install -r requirements.txt
```
## Usage
* Train
```angular2html
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python tools/train.py -cfg=configs/cub/r50_cub_448_e100_sgd_dcl_5x5_g4.yaml
```
* Test
```angular2html
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python tools/test.py -cfg=configs/cub/r50_cub_448_e100_sgd_dcl_5x5_g4.yaml
```
## Maintainers
* zhujian - *Initial work* - [zjykzj](https://github.com/zjykzj)
## Thanks
```
@InProceedings{Chen_2019_CVPR,
author = {Chen, Yue and Bai, Yalong and Zhang, Wei and Mei, Tao},
title = {Destruction and Construction Learning for Fine-Grained Image Recognition},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}
```
## Contributing
Anyone's participation is welcome! Open an [issue](https://github.com/ZJCV/DCL/issues) or submit PRs.
Small note:
* Git submission specifications should be complied
with [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0-beta.4/)
* If versioned, please conform to the [Semantic Versioning 2.0.0](https://semver.org) specification
* If editing the README, please conform to the [standard-readme](https://github.com/RichardLitt/standard-readme)
specification.
## License
[Apache License 2.0](LICENSE) © 2021 zjykzj