https://github.com/sally20921/NoisyStudent

"Self-training with Noisy Student improves ImageNet classification" pytorch implementation
https://github.com/sally20921/NoisyStudent

docker latex pytorch-ignite pytorch-implementation

Last synced: about 2 months ago
JSON representation

"Self-training with Noisy Student improves ImageNet classification" pytorch implementation

• Host: GitHub
• URL: https://github.com/sally20921/NoisyStudent
• Owner: sally20921
• License: mit
• Created: 2020-06-21T05:50:22.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2022-06-22T03:11:21.000Z (about 2 years ago)
• Last Synced: 2024-05-10T13:35:57.554Z (4 months ago)
• Topics: docker, latex, pytorch-ignite, pytorch-implementation
• Language: Python
• Homepage:
• Size: 1.16 MB
• Stars: 50
• Watchers: 2
• Forks: 6
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-image-classification - unofficial-pytorch: https://github.com/sally20921/NoisyStudent

README

        
# Self-training with Noisy Student improves ImageNet classification

Noisy Student Training is a semi-supervised training method which achieves 88.4% top-1 accuracy on ImageNet

and surprising gains on robustness and adversarial benchmarks.

Noisy Student Training is based on the self-training framework and trained with 4-simple steps:

1. Train a classifier on labeled data (teacher).

2. Infer labels on a much larger unlabeled dataset.

3. Train a larger classifier on the combined set, adding noise (noisy student).

4. Go to step 2, with student as teacher.