AI RESEARCH
M$^4$-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection
arXiv CS.CV
•
ArXi:2605.11760v1 Announce Type: new The Segment Anything Model 2 (SAM2) has emerged as a foundation model for universal segmentation. Owing to its generalizable visual representations, SAM2 has been successfully applied to various downstream tasks. However, extending SAM2 to the RGB-D video salient object detection (RGB-D VSOD) task encounters three challenges including limited spatial modeling of linear LoRA, insufficient employment of SAM's multi-scale features, and dependence of initialization on explicit prompts.