On Efficient Variants of Segment Anything Model: A Survey
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911589695750144 |
|---|---|
| author | Sun, Xiaorui Liu, Jun Shen, Heng Tao Zhu, Xiaofeng Hu, Ping |
| author_facet | Sun, Xiaorui Liu, Jun Shen, Heng Tao Zhu, Xiaofeng Hu, Ping |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04960 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On Efficient Variants of Segment Anything Model: A Survey Sun, Xiaorui Liu, Jun Shen, Heng Tao Zhu, Xiaofeng Hu, Ping Computer Vision and Pattern Recognition 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. |
| title | On Efficient Variants of Segment Anything Model: A Survey |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.04960 |