LLaFS: When Large Language Models Meet Few-Shot Segmentation

arXiv:2311.16926v4 Announce Type: replace
Abstract: This paper proposes LLaFS, the first attempt to leverage large language models (LLMs) in few-shot segmentation. In contrast to the conventional few-shot segmentation methods that only rely on the limited and biased information from the annotated support images, LLaFS leverages the vast prior knowledge gained by LLM as an effective supplement and directly uses the LLM to segment images in a few-shot manner. To enable the text-based LLM to handle image-related tasks, we carefully design …

abstract arxiv contrast cs.cv few-shot images information knowledge language language models large language large language models llm llms paper prior segmentation support type vast