/EVA

Exploring the Limits of Masked Visual Representation Learning at Scale (https://arxiv.org/abs/2211.07636)

Primary LanguagePythonMIT LicenseMIT

EVA: An Open Billion-Scale Vision Foundation Model

EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

Yuxin Fang2,1, Wen Wang3,1, Binhui Xie4,1, Quan Sun1, Ledell Wu1, Xinggang Wang2, Tiejun Huang1, Xinlong Wang1, Yue Cao1

1BAAI, 2HUST, 3ZJU, 4BIT

PWC
PWC
PWC
PWC
PWC
PWC
PWC
PWC
PWC
PWC

We launch EVA, a vision-centric foundation model to Explore the limits of Visual representation at scAle using only publicly accessible data and academic resources. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features (i.e., CLIP features) conditioned on visible image patches. Via this pretext task, we can efficiently scale up EVA to one billion parameters, and sets new records on a broad range of representative vision downstream tasks.

EVA is the first open-sourced billion-scale vision foundation model that achieves state-of-the-art performance on a broad range of downstream tasks.

News

$\color{red}{\text{All the code and 16x state-of-the-art billion-scale models are open-sourced!}}$

Catalog

All EVA model checkpoints (16 in total) are now available at 🤗 Hugging Face Models. Try them out!

Summary of EVA's performance

image & video classification

image classificationvideo classification
model#param.IN-1KIN-1K, zero-shot12 avg. zero-shotK400K600K700
EVA1.0B89.778.572.5+89.789.882.9

object detection & segmentation

COCO det & ins segLVIS det & ins segsem seg
model#param.det (test)det (val)seg (test)seg (val)detsegCOCO-StuffADE20K
EVA1.0B64.764.555.555.062.255.053.462.3

Citation

If you find our work helpful, please star🌟 this repo and cite📑 our paper. Thanks for your support!

@article{EVA,
  title={EVA: Exploring the Limits of Masked Visual Representation Learning at Scale},
  author={Fang, Yuxin and Wang, Wen and Xie, Binhui and Sun, Quan and Wu, Ledell and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
  journal={arXiv preprint arXiv:2211.07636},
  year={2022}
}

License

The content of this project itself is licensed under LICENSE.

Contact

  • For help and issues associated with EVA, or reporting a bug, please open a GitHub Issue. Let's build a better & stronger EVA together :)

  • 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 Yue Cao (caoyue@baai.ac.cn) and Xinlong Wang (wangxinlong@baai.ac.cn).

↳ Stargazers

Stargazers repo roster for @baaivision/EVA

↳ Forkers

Forkers repo roster for @baaivision/EVA