https://github.com/google-research/syn-rep-learn
Learning from synthetic data - code and models
https://github.com/google-research/syn-rep-learn
Last synced: 3 months ago
JSON representation
Learning from synthetic data - code and models
- Host: GitHub
- URL: https://github.com/google-research/syn-rep-learn
- Owner: google-research
- License: apache-2.0
- Created: 2023-10-04T19:08:31.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-01-06T15:26:31.000Z (over 1 year ago)
- Last Synced: 2025-02-28T21:41:12.966Z (3 months ago)
- Language: Python
- Homepage:
- Size: 4.9 MB
- Stars: 310
- Watchers: 12
- Forks: 14
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
# Syn-Rep-Learn
This repo contains research studies of learning from synthetic data (mostly images), including:
- `StableRep` - [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://arxiv.org/abs/2306.00984). Yonglong Tian*, Lijie Fan*, Phillip Isola, Huiwen Chang, Dilip Krishnan.
- `Scaling` - [Scaling Laws of Synthetic Images for Model Training ... for Now](https://arxiv.org/abs/2312.04567). Lijie Fan*, Kaifeng Chen, Dilip Krishnan, Dina Katabi, Phillip Isola, Yonglong Tian*.
- `SynCLR` - [Learning Vision from Models Rivals Learning Vision from Data](SynCLR/assets/synclr_paper.pdf). Yonglong Tian*, Lijie Fan*, Kaifeng Chen, Dina Katabi, Dilip Krishnan, Phillip Isola.
## Disclaimer
This is not an officially supported Google product.
## License
Apache2 license.
## Contact
Yonglong Tian ([email protected])
Lijie Fan ([email protected])