On Efficient Variants of Segment Anything Model: A Survey

arXiv:2410.04960v5 Announce Type: replace Abstract: The Segment Anything Model (SAM) is a foundational model for image segmentation tasks, known for its strong generalization across diverse applications. However, its impressive performance comes with significant computational and resource demands, making it challenging to deploy in resource-limited environments such as edge devices. To address this, a variety of SAM variants have been proposed to enhance efficiency while keeping accuracy. This survey provides the first comprehensive review of these efficient SAM variants. We begin by exploring the motivations driving this research. We then present core techniques used in SAM and model acceleration. This is followed by a detailed exploration of SAM acceleration strategies, categorized by approach, and a discussion of several future research directions. Finally, we offer a unified and extensive evaluation of these methods across various hardware, assessing their efficiency and accuracy on representative benchmarks, and providing a clear comparison of their overall performance.

Related

• Mitigating Domain Drift in Multi Species Segmentation with DINOv2: A Cross-Domain Evaluation in Herbicide Research Trials
• Horticultural Temporal Fruit Monitoring via 3D Instance Segmentation and Re-Identification using Colored Point Clouds
• Interactive Interface For Semantic Segmentation Dataset Synthesis
• Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation
• Vision-Language Foundation Models for Comprehensive Automated Pavement Condition Assessment

Source: arXiv cs.CV | 2026-04-15