C2I-DINO: Category-to-Instance Discrimination for Remote Sensing Visual Grounding
A category-to-instance framework built on Grounding DINO (C2I-DINO), which introduces category-focused prompting (CFP), which retrieves learnable category-specific suffix vectors and appends them to the projected text memory before cross-modal fusion, and spatial instance learning (SIL), which uses ranking and suppress...