M$^4$-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Jiyuan, Lin, Jia, Zhou, Xiaofei, Cong, Runmin, Liu, Deyang, Liu, Zhi
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910211661365248
author Liu, Jiyuan
Lin, Jia
Zhou, Xiaofei
Cong, Runmin
Liu, Deyang
Liu, Zhi
author_facet Liu, Jiyuan
Lin, Jia
Zhou, Xiaofei
Cong, Runmin
Liu, Deyang
Liu, Zhi
contents 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. To address the issues, we present Multi-Modal Mixture-of-Experts with Memory-Augmented SAM (M$^4$-SAM), which equips SAM2 with modality-related PEFT, hierarchical feature fusion, and prompt-free memory initialization. Firstly, we inject Modality-Aware MoE-LORA, which employs convolutional experts to encode local spatial priors and introduces a modality dispatcher for efficient multi-modal fine-tuning, into SAM2's encoder. Secondly, we deploy Gated Multi-Level Feature Fusion, which hierarchically aggregates multi-scale encoder features with an adaptive gating mechanism, to balance spatial details and semantic context. Finally, to conduct zero-shot VSOD without manual prompts, we utilize a Pseudo-Guided Initialization, where a coarse mask is regarded as a pseudo prior and used to bootstrap the memory bank. Extensive experiments demonstrate that M$^4$-SAM achieves the state-of-the-art performance across all evaluation metrics on three public RGB-D VSOD datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11760
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle M$^4$-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection
Liu, Jiyuan
Lin, Jia
Zhou, Xiaofei
Cong, Runmin
Liu, Deyang
Liu, Zhi
Computer Vision and Pattern Recognition
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. To address the issues, we present Multi-Modal Mixture-of-Experts with Memory-Augmented SAM (M$^4$-SAM), which equips SAM2 with modality-related PEFT, hierarchical feature fusion, and prompt-free memory initialization. Firstly, we inject Modality-Aware MoE-LORA, which employs convolutional experts to encode local spatial priors and introduces a modality dispatcher for efficient multi-modal fine-tuning, into SAM2's encoder. Secondly, we deploy Gated Multi-Level Feature Fusion, which hierarchically aggregates multi-scale encoder features with an adaptive gating mechanism, to balance spatial details and semantic context. Finally, to conduct zero-shot VSOD without manual prompts, we utilize a Pseudo-Guided Initialization, where a coarse mask is regarded as a pseudo prior and used to bootstrap the memory bank. Extensive experiments demonstrate that M$^4$-SAM achieves the state-of-the-art performance across all evaluation metrics on three public RGB-D VSOD datasets.
title M$^4$-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.11760