AI Rank
EN
← 开源
bhanML

Co-teaching

NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

Model DevelopmentDeep Learning FrameworksPython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
521
Star
109
Fork
+1
本周
3
贡献者
创建于 2018-10-17 · 更新于 2026-10-12 · 今日第 17833 名
主要开发者
bhanMLxingruiyuquanmingyao

bhanML/Co-teaching 排名第 17,833，有 521 个星标。

同类别比较

bhanML/Co-teaching 排名第 17,833，此处有 8 个同类条目；airalcorn2/Deep-Semantic-Similarity-Model 排名第 17,832。

同类别比较
名称排名指标
NVlabs/DeepInversion17,828
语言:
Python
星标数:
521
分叉数:
87
简介:
Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)
PKU-MARL/Multi-Agent-Transformer17,829
语言:
Python
星标数:
521
分叉数:
94
Zielon/INSTA17,831
语言:
C++
星标数:
521
分叉数:
44
简介:
INSTA - Instant Volumetric Head Avatars [CVPR2023]
airalcorn2/Deep-Semantic-Similarity-Model17,832
语言:
Python
星标数:
521
分叉数:
178
简介:
My Keras implementation of the Deep Semantic Similarity Model (DSSM)/Convolutional Latent Semantic Model (CLSM) described here: http://research.microsoft.com/pubs/226585/cikm2014_cdssm_final.pdf.
google-deepmind/narrativeqa17,837
语言:
Shell
星标数:
521
分叉数:
70
简介:
This repository contains the NarrativeQA dataset. It includes the list of documents with Wikipedia summaries, links to full stories, and questions and answers.
kLabUM/rrcf17,838
语言:
Python
星标数:
521
分叉数:
118
简介:
🌲 Implementation of the Robust Random Cut Forest algorithm for anomaly detection on streams
lucasjinreal/keras_frcnn17,840
语言:
Python
星标数:
521
分叉数:
272
简介:
Keras Implementation of faster-rcnn
Deeachain/Segmentation-Pytorch17,844
语言:
Python
星标数:
520
分叉数:
75
简介:
Semantic Segmentation in Pytorch. Network include: FCN、FCN_ResNet、SegNet、UNet、BiSeNet、BiSeNetV2、PSPNet、DeepLabv3_plus、 HRNet、DDRNet
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Deep Learning Frameworks
星标数521
分叉数109
贡献者3
创建日期2018-10-17
更新日期2026-10-12
1 天星标数0
7 天星标数1
排名17,833
上次排名17,617
排名变化-216
7 天星标排名11,523
上次 7 天星标排名11,579
7 天星标排名变化56
总星标排名18,759
上次总星标排名18,732
总星标排名变化-27
国家China
README 摘录

Co-teaching NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels (Pytorch implementation). Another related work in NeurIPS'18: Masking: A New Perspective of Noisy Supervision Code available: ======== This is the code for the paper: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels Bo Han*, Quanming Yao*, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, Masashi Sugiyama To be presented at NeurIPS 2018. If you find this code useful

in your research then please cite Setups All code was developed and tested on a single machine equiped with a NVIDIA K80 GPU. AutoML Please check the automated machine learning (AutoML) version of Co-teaching in Searching to Exploit Memorization Effect in Learning from Corrupted Labels.

常见问题

记录了多少星标和分叉？

bhanML/Co-teaching 有 521 个星标和 109 个分叉。

仓库排名是多少？

bhanML/Co-teaching 排名第 17,833。

记录的语言和类别是什么？

bhanML/Co-teaching 有 521 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

bhanML/Co-teaching 与 airalcorn2/Deep-Semantic-Similarity-Model 比较，后者排名第 17,832，有 521 个星标。

README

Co-teaching

NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels (Pytorch implementation).

Another related work in NeurIPS'18:

Masking: A New Perspective of Noisy Supervision

Code available: https://github.com/bhanML/Masking

========

This is the code for the paper: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
Bo Han*, Quanming Yao*, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, Masashi Sugiyama
To be presented at NeurIPS 2018.

If you find this code useful in your research then please cite

@inproceedings{han2018coteaching,
  title={Co-teaching: Robust training of deep neural networks with extremely noisy labels},
  author={Han, Bo and Yao, Quanming and Yu, Xingrui and Niu, Gang and Xu, Miao and Hu, Weihua and Tsang, Ivor and Sugiyama, Masashi},
  booktitle={NeurIPS},
  pages={8535--8545},
  year={2018}
}

Setups

All code was developed and tested on a single machine equiped with a NVIDIA K80 GPU. The environment is as bellow:

  • CentOS 7.2
  • CUDA 8.0
  • Python 2.7.12 (Anaconda 4.1.1 64 bit)
  • PyTorch 0.3.0.post4
  • numpy 1.14.2

Install PyTorch via:

pip install http://download.pytorch.org/whl/cu80/torch-0.3.0.post4-cp27-cp27mu-linux_x86_64.whl

Running Co-teaching on benchmark datasets (MNIST, CIFAR-10 and CIFAR-100)

Here is an example:

python main.py --dataset cifar10 --noise_type symmetric --noise_rate 0.5

Performance

(Flipping, Rate) MNIST CIFAR-10 CIFAR-100
(Pair, 45%) 87.58% 72.85% 34.40%
(Symmetry, 50%) 91.68% 74.49% 41.23%
(Symmetry, 20%) 97.71% 82.18% 54.36%

Contact: Xingrui Yu (xingrui.yu@student.uts.edu.au); Bo Han (bo.han@riken.jp).

AutoML

Please check the automated machine learning (AutoML) version of Co-teaching in

  • Searching to Exploit Memorization Effect in Learning from Corrupted Labels. ICML-2020 paper code
排名相邻
同类项目