Sep 2026
Multi-modal interaction enhanced segment anything model (MIE-SAM) for RGB-T salient object detection.
A Multi-modal Interaction Enhanced Segment Anything Model (MIE-SAM) that reconfigures SAM's image encoder into a weight-sharing dual-branch image encoders, and translates the fused features into the fine-grained saliency map in an entirely prompt-free, end-to-end manner.
Ze Li, Ying-Ying Zhang, Shuai Zhang et al.
· Neural Networks · 0 citations