HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model
This is InternVL2_5-HiMTok-8B model fine-tuned on the refcoco series train dataset.
If you find this project useful in your research, please consider citing:
@article{wang2025himtok,
title={HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model},
author={Wang, Tao and Cheng, Changxu and Wang, Lingfeng and Chen, Senda and Zhao, Wuyue},
journal={arXiv preprint arXiv:2503.13026},
year={2025}
}