Machine learningDeep Learning, State Space Models
视觉曼巴
视觉曼巴（Vision Mamba）是一种于2024年提出的高效状态空间模型方法，用于图像理解，它将线性复杂度序列模型曼巴（Mamba）应用于计算机视觉领域。通过将图像块重构为序列并使用状态空间模型，视觉曼巴在保持线性计算复杂度的同时，实现了与Transformer相当的准确率。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X. (2024). Vision Mamba: Efficient state space models for image understanding. In International Conference on Machine Learning. link ↗
如何引用本页
ScholarGate. (2026, June 3). Vision Mamba: Efficient State Space Models for Image Understanding. ScholarGate. https://scholargate.app/zh/deep-learning/vision-mamba
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- Mamba（状态空间模型）深度学习↔ compare
- 时空图卷积网络深度学习↔ compare
- Swin Transformer深度学习↔ compare
- Vision Transformer深度学习↔ compare