https://github.com/baaivision/EVA

EVA Series: Visual Representation Fantasies from BAAI
https://github.com/baaivision/EVA

foundation-models representation-learning vision-transformer

Last synced: 29 days ago
JSON representation

EVA Series: Visual Representation Fantasies from BAAI

• Host: GitHub
• URL: https://github.com/baaivision/EVA
• Owner: baaivision
• License: mit
• Created: 2022-11-14T07:54:32.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2024-08-01T14:49:48.000Z (9 months ago)
• Last Synced: 2024-10-15T09:04:43.579Z (6 months ago)
• Topics: foundation-models, representation-learning, vision-transformer
• Language: Python
• Homepage:
• Size: 8.61 MB
• Stars: 2,262
• Watchers: 30
• Forks: 165
• Open Issues: 71
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-multi-modal - https://github.com/baaivision/EVA
• awesome-multi-modal - https://github.com/baaivision/EVA
• awesome-vision-language-pretraining - EVA

README

        


EVA: Visual Representation Fantasies from BAAI




![summary_tab](assets/eva_pipeline.png)

- [**EVA-01**](EVA-01) (CVPR 2023, 🌟highlight🌟) - Exploring the Limits of Masked Visual Representation Learning at Scale

- [**EVA-02**](EVA-02) (Image and Vision Computing) - A Visual Representation for Neon Genesis

- [**EVA-CLIP**](EVA-CLIP) (Arxiv 2023) - Improved Training Techniques for CLIP at Scale

- [**EVA-CLIP-18B**](EVA-CLIP-18B) (Arxiv 2024) - EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

  

- [**EVA @ Hugging Face 🤗 & `timm`**](https://huggingface.co/timm/eva02_large_patch14_448.mim_m38m_ft_in1k)

- [**EVA-CLIP @ Hugging Face 🤗 & `timm`**](https://huggingface.co/timm/eva02_enormous_patch14_plus_clip_224.laion2b_s9b_b144k)

- [**EVA-CLIP @ `open_clip`**](https://github.com/mlfoundations/open_clip/blob/main/src/open_clip/model_configs/EVA02-E-14-plus.json) 

## Contact

- **We are hiring** at all levels at BAAI Vision Team, including full-time researchers, engineers and interns. 

If you are interested in working with us on **foundation model, self-supervised learning and multimodal learning**, please contact [Xinlong Wang](https://www.xloong.wang/) (`[email protected]`).

## License

The content of this project itself is licensed under [LICENSE](LICENSE).

## Misc



[![Stargazers repo roster for @baaivision/EVA](https://bytecrank.com/nastyox/reporoster/php/stargazersSVG.php?user=baaivision&repo=EVA)](https://github.com/baaivision/EVA/stargazers)

[![Forkers repo roster for @baaivision/EVA](https://bytecrank.com/nastyox/reporoster/php/forkersSVG.php?user=baaivision&repo=EVA)](https://github.com/baaivision/EVA/network/members)

[![Star History Chart](https://api.star-history.com/svg?repos=baaivision/EVA&type=Date)](https://star-history.com/#baaivision/EVA&Date)