SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation
This addresses the challenge of precise visual grounding for AI systems that combine language and vision, though it appears incremental as it builds on existing SAM and MLLM frameworks.
The paper tackles the problem of enabling multi-modal large language models to perform pixel-level segmentation tasks by integrating the Segment Anything Model (SAM) without major architectural changes, achieving effective results on public benchmarks.
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.