TY  - JOUR
T1  - Zero-shot Referring Image Segmentation using Referring Expression Augmentation and Mask Aggregation
AU  - Song, Seungheon 
AU  - Kim, Sungsik 
AU  - Seo, Junghyeon 
AU  - Lee, Jaekoo 
JO  - Journal of KIISE, JOK
PY  - 2026
DA  - 2026/1/14
DO  - 10.5626/JOK.2026.53.1.15
KW  - computer vision
KW  - image segmentation
KW  - reference image segmentation
KW  - large language model
AB  - 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.