Giter VIP home page Giter VIP logo

label-noise-robust-training's Introduction

Paper 1

Noise Robust Learning with Hard Example Aware for Pathological Image classification

Tweet

Implementation detail for our paper "Noise Robust Learning with Hard Example Aware for Pathological Image classification", this code also includes further resaerch beyound this paper.

Citation

Please cite this paper in your publications if it helps your research:

@inproceedings{peng2020noise,
  title={Noise Robust Learning with Hard Example Aware for Pathological Image classification},
  author={Peng, Ting and Zhu, Chuang and Luo, Yihao and Liu, Jun and Wang, Ying and Jin, Mulan},
  booktitle={2020 IEEE 6th International Conference on Computer and Communications (ICCC)},
  pages={1903--1907},
  year={2020},
  organization={IEEE}
}

Dataset

DigestPath 2019: https://digestpath2019.grand-challenge.org/Dataset/

Colorectal dataset (contributed by this paper):contains 4198 microscopy images, which are distributed as follows: adenoma, polyp, adenocarcinoma, gastrointestinal stromal tumor, and neuroendocrine tumor

Envs

  • Pytorch 1.0
  • Python 3+
  • cuda 9.0+

Training

$ cd code/
# train label noise dataset and record training history
$ python iter_train.py --cached_data_file='pickle_data/digest_20.p'
# uncomment "detect label noise" code block in iter_train.py and apply label noise detect algorithm
$ python iter_train.py 
# label correction
$ python pre_iter.py
# train neural network on processed label noise dataset (apply different loss functions)
$ python train.py
# co-teaching training
$ python co-teaching.py

Paper 2

Pathological Image Classification Based on Hard Example Guided CNN

For the implementation for our paper "Pathological Image Classification Based on Hard Example Guided CNN", please refer to code/code_access/train_history.py

Citation

Please cite this paper in your publications if it helps your research:

@article{wang2020pathological,
  title={Pathological image classification based on hard example guided CNN},
  author={Wang, Ying and Peng, Ting and Duan, Jiajia and Zhu, Chuang and Liu, Jun and Ye, Jiandong and Jin, Mulan},
  journal={IEEE Access},
  volume={8},
  pages={114249--114258},
  year={2020},
  publisher={IEEE}
}

Contact

label-noise-robust-training's People

Contributors

bupt-ai-cz avatar hakeyi avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

Forkers

trellixvulnteam

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.