A Survey on Mamba Architecture for Vision Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909487989784576 |
|---|---|
| author | Ibrahim, Fady Liu, Guangjun Wang, Guanghui |
| author_facet | Ibrahim, Fady Liu, Guangjun Wang, Guanghui |
| contents | Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these limitations, the Mamba architecture utilizes state-space models (SSMs) for linear scalability, efficient processing, and improved contextual awareness. This paper investigates Mamba architecture for visual domain applications and its recent advancements, including Vision Mamba (ViM) and VideoMamba, which introduce bidirectional scanning, selective scanning mechanisms, and spatiotemporal processing to enhance image and video understanding. Architectural innovations like position embeddings, cross-scan modules, and hierarchical designs further optimize the Mamba framework for global and local feature extraction. These advancements position Mamba as a promising architecture in computer vision research and applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07161 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey on Mamba Architecture for Vision Applications Ibrahim, Fady Liu, Guangjun Wang, Guanghui Computer Vision and Pattern Recognition Artificial Intelligence Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these limitations, the Mamba architecture utilizes state-space models (SSMs) for linear scalability, efficient processing, and improved contextual awareness. This paper investigates Mamba architecture for visual domain applications and its recent advancements, including Vision Mamba (ViM) and VideoMamba, which introduce bidirectional scanning, selective scanning mechanisms, and spatiotemporal processing to enhance image and video understanding. Architectural innovations like position embeddings, cross-scan modules, and hierarchical designs further optimize the Mamba framework for global and local feature extraction. These advancements position Mamba as a promising architecture in computer vision research and applications. |
| title | A Survey on Mamba Architecture for Vision Applications |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.07161 |