Skip to content

About

[NeurIPS2024] $\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise

Topics

Resources

Stars

10 stars

Watchers

1 watching

Forks

Latest commit

 

History

14 Commits

Folders and files

Repository files navigation

$\epsilon$-Softmax

Approximating One-Hot Vectors for Mitigating Label Noise

Official PyTorch Implementation · NeurIPS 2024

arXiv License: MIT

Overview · Poster · Usage · Examples · Citation · Contact


✨ Overview

This repository provides training scripts for benchmark, semi-supervised, and real-world noisy-label learning.

  • Losses: $\epsilon$-softmax with CE or FL, combined with MAE.
  • Noise types: symmetric, asymmetric, instance-dependent, human, and real-world.
  • Datasets: CIFAR-10, CIFAR-100, CIFAR-N, WebVision, and Clothing1M.

Note

In the code, ECE and EFL denote CE and FL with $\epsilon$-softmax, respectively. Their combinations with MAE are named ECEandMAE and EFLandMAE.

🖼️ Poster

ε-Softmax poster

🛠️ Usage

git clone https://github.com/cswjl/eps-softmax.git && cd eps-softmax
Setting Entry point Datasets Noise types
Benchmark main.py cifar10, cifar100 symmetric, asymmetric, dependent, human
Semi-supervised main_semi.py cifar10, cifar100 symmetric, asymmetric, dependent, human
Real-world main_real_world.py webvision, clothing1m Real-world label noise
Argument Description Examples
--dataset Dataset cifar10, cifar100, webvision, clothing1m
--loss Loss function (benchmark and real-world) ECEandMAE, EFLandMAE, CE, GCE
--noise_type Noise type (benchmark and semi-supervised) symmetric, asymmetric, dependent, human
--noise_rate Noise rate, or CIFAR-N label set with human 0.8, worst, noisy100
--root Dataset root directory ../data (default)
📂 Repository structure
eps-softmax/
├── main.py                 # Benchmark training
├── main_semi.py            # Semi-supervised training
├── main_real_world.py      # Real-world dataset training
├── losses.py               # Loss function implementations
├── config.py               # Loss and regularization configurations
├── models.py               # Network architectures
├── utils.py                # Training and evaluation utilities
└── datasets/               # Data loaders, noise annotations, and dataset lists

🚀 Examples

# CIFAR-10 · 80% symmetric noise · ECE + MAE
python3 main.py --dataset cifar10 --noise_type symmetric --noise_rate 0.8 --loss ECEandMAE

# CIFAR-10N · worst human labels · ECE + MAE (Semi)
python3 main_semi.py --dataset cifar10 --noise_type human --noise_rate worst

# WebVision · real-world noise · ECE + MAE
python3 main_real_world.py --dataset webvision --loss ECEandMAE

🎓 Citation

If you find this work useful, please cite our paper:

@article{wang2024epsilon,
  title={$\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise},
  author={Wang, Jialiang and Zhou, Xiong and Zhai, Deming and Jiang, Junjun and Ji, Xiangyang and Liu, Xianming},
  journal={Advances in Neural Information Processing Systems},
  volume={37},
  pages={32012--32038},
  year={2024}
}

📬 Contact

Questions about the paper or code? Contact Jialiang Wang at cswjl@stu.hit.edu.cn.


⭐ Star us on GitHub — it motivates us a lot!

About

[NeurIPS2024] $\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise

Topics

Resources

Stars

10 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages