DGSSM: Diffusion guided state-space models for multimodal salient object detection

arXiv:2604.17585v1 Announce Type: cross Abstract: Salient object detection (SOD) requires modeling both long-range contextual dependencies and fine-grained structural details, which remains challenging for convolutional, transformer-based, and Mamba-based state space models. While recent Mamba-based state space approaches enable efficient global reasoning, they often struggle to recover precise object boundaries. In contrast, diffusion models capture strong structural priors through iterative de