Comprehensive Multi-Modal Interactions for Referring Image Segmentation

We investigate Referring Image Segmentation (RIS), which outputs a segmentation map corresponding to the natural language description. Addressing RIS efficiently requires considering the interactions happening \emph{across} visual and linguistic modalities and the interactions \emph{within} each modality. Existing methods are limited because they either compute different forms of interactions \emph{sequentially} (leading to error propagation) or \emph{ignore} intramodal interactions. We address this limitation by performing all three interactions \emph{simultaneously} through a Synchronous Multi-Modal Fusion Module (SFM). Moreover, to produce refined segmentation masks, we propose a novel Hierarchical Cross-Modal Aggregation Module (HCAM), where linguistic features facilitate the exchange of contextual information across the visual hierarchy. We present thorough ablation studies and validate our approach's performance on four benchmark datasets, showing considerable performance gains over the existing state-of-the-art (SOTA) methods.