BAAI / tokenize-anything

We present T okenize A nything via P rompting, a unified and promptable model capable of simultaneously segmenting, recognizing, and captioning arbitrary regions, with flexible visual prompts (point, box and sketch). The model is trained with exhaustive segmentation masks sourced from SA-1B, coupled with semantic priors from a pre-trained EVA-CLIP with 5 billion parameters.

Installation

See Github Page .

Models

Model weights

V1.1 Release Notes

• Three versions of the model are available with different image encoders.
• Use a longer pre-training and fine-tuning schedule (improved segmentation and caption performance).
• Apply weight decay for all bias parameters (avoid FP16 overflow in QK matmul).
• Sample point prompts from predicted mask instead of GT box during VG training.

V1.0 Release Notes

• Two versions of the model are available with different image encoders.
• Original paper results.

Concept weights

Note : You can generate these weights following the Concept Guide .

License

Apache License 2.0

Citation

@article{pan2023tap,
  title={Tokenize Anything via Prompting},
  author={Pan, Ting and Tang, Lulu and Wang, Xinlong and Shan, Shiguang},
  journal={arXiv preprint arXiv:2312.09128},
  year={2023}
}

Acknowledgement

We thank the repositories: SAM , EVA , LLaMA , FlashAttention , Gradio , Detectron2 and CodeWithGPU .