Mamba用状态空间模型替代注意力机制，提升视觉任务效率。
A Survey on Mamba Architecture for Vision Applications
- 用状态空间模型实现线性复杂度，取代传统Transformer的二次计算
- 提出ViM和VideoMamba，支持图像与视频的双向扫描与时空建模
- 适合追求高效、长序列视觉处理的研究者与工程师
Transformers已成为目标检测、语义分割和视频理解等视觉任务的基础架构，但其注意力机制的二次复杂度带来可扩展性挑战。为解决这一问题，Mamba架构采用状态空间模型（SSMs）实现线性可扩展性、高效处理和更优的上下文感知能力。本文综述了Mamba架构在视觉领域的应用及最新进展，包括引入双向扫描、选择性扫描机制和时空处理的Vision Mamba（ViM）与VideoMamba，以及位置编码、跨扫描模块和分层设计等架构创新，有效优化了全局与局部特征提取。这些改进使Mamba成为计算机视觉研究与应用中的有前景架构。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。