Generalizable Entity Grounding via Assistance of Large Language Model

In this work, we propose a novel approach to densely ground visual entities from a long caption. We leverage a large multimodal model (LMM) to extract semantic nouns, a class-agnostic segmentation model to generate entity-level segmentation, and the proposed multi-modal feature fusion module to associate each semantic noun with its corresponding segmentation mask. Additionally, we introduce a strategy of encoding entity segmentation masks into a colormap, enabling the preservation of fine-grained predictions from features of high-resolution masks. This approach allows …

class cs.cv extract feature fusion generate language language model large language large language model lmm modal multi-modal multimodal multimodal model novel segmentation semantic via visual work