TVI-MFAN: A Text–Visual Interaction Multilevel Feature Alignment Network for Visual Grounding in Remote Sensing

Visual grounding for remote sensing (RSVG) focuses on localizing specific objects in remote sensing (RS) imagery based on linguistic expressions. Existing methods typically employ pre-trained models to locate the referenced objects. However, due to the insufficient capability of cross-modal interaction and alignment, the extracted visual features may suffer from semantic drift, limiting the performance of RSVG. To address this, the article introduces a novel RSVG framework named the text–visual interaction multilevel feature alignment network (TVI-MFAN), which leverages a text–visual interaction attention (TVIA) module to dynamically generate adaptive weights and biases at both spatial and channel dimensions, enabling the visual feature to focus on relevant linguistic expressions. Additionally, a multilevel feature alignment network (MFAN) aggregates contextual information by using cross-modal alignment to enhance features and suppress irrelevant regions. Experiments demonstrate that the proposed method achieves 75.65% and 80.24% (2.42% and 3.1% absolute improvement) accuracy on the OPT-RSVG and DIOR-RSVG dataset, validating its effectiveness.