Seungheon Song  Sungsik Kim  Junghyeon Seo  Jaekoo Lee

10.5626/JOK.2026.53.1.15

computer vision Image Segmentation reference image segmentation Large Language Model

With advancements in computer vision technology, image segmentation tasks are increasingly utilized across various fields. Among these, reference image segmentation is particularly valuable for achieving precise regional segmentation based on user instructions. In this paper, we introduce a reference image segmentation framework inspired by human cognitive processes, which utilizes prior knowledge to recognize objects. Our method employs a large language model to infer various visual attributes of objects and integrates these inferences with mask proposals. Consequently, our approach enhances oIoU and mIoU performance by 0.41% and 0.74%, respectively, compared to existing methods on the RefCOCO, RefCOCO+, and RefCOCOg benchmark datasets.