RPL - GitLite

KO | EN

gitlite — search

#python #llm #golang #go #rust #deep-learning #linux #docker #kubernetes #vue #pytorch #mcp #openai #open-source

RPL

(★ 131)

[ICCV'23] Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation

파일 탐색기

최종 버전 다운로드 (.zip)

- - .gitkeep
- - .gitkeep
- before_start.md
- installation.md
- requirements.txt
- result.md
- Dockerfile
- - config.py
- - cityscapes_coco.py
  - data_loader.py
  - mix_ood_sampler.py
- - download_to_pvc.py
- - engine.py
  - evaluator.py
  - lr_policy.py
  - trainer.py
- - PositiveEnergy.py
- - mynn.py
  - network.py
  - resnet.py
  - wide_network.py
  - wide_resnet_base.py
  - wider_resnet.py
- - aug.py
  - conv_2_5d.py
  - img_utils.py
  - logger.py
  - metric.py
  - pyt_utils.py
  - smiyc_metrics.py
  - wandb_upload.py
- main.py
- test.py
- valid.py
- - config.py
- - cityscapes_coco.py
  - data_loader.py
  - mix_ood_sampler.py
- - download_to_pvc.py
- - engine.py
  - evaluator.py
  - lr_policy.py
  - trainer.py
- - CoroCL.py
  - PositiveEnergy.py
- - mynn.py
  - network.py
  - resnet.py
  - wide_network.py
  - wide_resnet_base.py
  - wider_resnet.py
- - aug.py
  - conv_2_5d.py
  - img_utils.py
  - logger.py
  - metric.py
  - pyt_utils.py
  - smiyc_metrics.py
  - wandb_upload.py
- main.py
- test.py
- valid.py
LICENSE
README.md
rpl.yml

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/yyliu01/RPL

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd RPL

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Docker

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.

docker build -f k8s_launch/Dockerfile -t rpl .

Dockerfile을 기반으로 실행 가능한 이미지를 빌드합니다.

docker run -p 8080:80 rpl

빌드된 이미지를 실제 컨테이너로 실행합니다.

✅ 터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# RPL
> [Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation](https://arxiv.org/pdf/2211.14512.pdf)
>
> by Yuyuan Liu*, Choubo Ding*, [Yu Tian](https://yutianyt.com/), [Guansong Pang](https://sites.google.com/site/gspangsite),
> [Vasileios Belagiannis](https://campar.in.tum.de/Main/VasileiosBelagiannis), 
> [Ian Reid](https://cs.adelaide.edu.au/~ianr/) and [Gustavo Carneiro](https://cs.adelaide.edu.au/~carneiro/)
> 
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/residual-pattern-learning-for-pixel-wise-out/anomaly-detection-on-fishyscapes-1)](https://paperswithcode.com/sota/anomaly-detection-on-fishyscapes-1?p=residual-pattern-learning-for-pixel-wise-out)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/residual-pattern-learning-for-pixel-wise-out/anomaly-detection-on-road-anomaly)](https://paperswithcode.com/sota/anomaly-detection-on-road-anomaly?p=residual-pattern-learning-for-pixel-wise-out)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/residual-pattern-learning-for-pixel-wise-out/anomaly-detection-on-fishyscapes-l-f)](https://paperswithcode.com/sota/anomaly-detection-on-fishyscapes-l-f?p=residual-pattern-learning-for-pixel-wise-out)

<img src="https://github.com/yyliu01/RPL/assets/102338056/4307ce17-9c44-4e19-82b7-b0508f51ff28.png" width="700" height="300" />

### Installation
please install the dependencies and dataset based on this [***installation***](./docs/installation.md) document.

### Getting start
please follow this [***instruction***](./docs/before_start.md) document to reproduce our results.

### Results
our training logs and checkpoints are in this [***result***](./docs/result.md) page.

## Acknowledgement & Citation

Our code is highly based on the [PEBAL](https://github.com/tianyu0207/PEBAL). 
Please consider citing them in your publications if they help your research.
```bibtex
@inproceedings{liu2023residual,
  title={Residual pattern learning for pixel-wise out-of-distribution detection in semantic segmentation},
  author={Liu, Yuyuan and Ding, Choubo and Tian, Yu and Pang, Guansong and Belagiannis, Vasileios and Reid, Ian and Carneiro, Gustavo},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={1151--1161},
  year={2023}
}
@inproceedings{tian2022pixel,
  title={Pixel-wise energy-biased abstention learning for anomaly segmentation on complex urban driving scenes},
  author={Tian, Yu and Liu, Yuyuan and Pang, Guansong and Liu, Fengbei and Chen, Yuanhong and Carneiro, Gustavo},
  booktitle={European Conference on Computer Vision},
  pages={246--263},
  year={2022},
  organization={Springer}
}
```
#### TODO
- [x] RPL code has been released.
- [x] RPL+CoroCL code has been released.
- [x] The results based on extra training sets (e.g., Vistas, Wilddash2) have been released.