SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation

Abstract

We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without requiring excessive modifications to the existing model architecture or adding specialized tokens. We introduce an inquiry-based approach that can effectively find prompt points for SAM to perform segmentation based on MLLM. It combines detailed visual information with the powerful expressive capabilities of large language models in a unified language-based manner without additional computational overhead in learning. Experimental results on pubic benchmarks demonstrate the effectiveness of our approach.

Cite

Text

Chen et al. "SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73004-7_19

Markdown

[Chen et al. "SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/chen2024eccv-sam4mllm/) doi:10.1007/978-3-031-73004-7_19

BibTeX

@inproceedings{chen2024eccv-sam4mllm,
  title     = {{SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation}},
  author    = {Chen, Yi-Chia and Li, Wei-Hua and Sun, Cheng and Wang, Yu-Chiang Frank and Chen, Chu-Song},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-73004-7_19},
  url       = {https://mlanthology.org/eccv/2024/chen2024eccv-sam4mllm/}
}