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

TL;DR

SAM4MLLM is a novel method that combines SAM with MLLMs to perform pixel-aware segmentation tasks efficiently, leveraging language-based prompts without significant architectural changes.

Contribution

It introduces an inquiry-based approach for prompt point selection, enabling effective segmentation with minimal modifications to existing models.

Findings

Demonstrates improved segmentation accuracy on public benchmarks.

Shows that the method requires no additional training overhead.

Validates the approach's effectiveness through extensive experiments.

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.