Vision Mamba: A Comprehensive Survey and Taxonomy
Xiao Liu, Chenxu Zhang, Lei Zhang

TL;DR
This paper provides a comprehensive survey and taxonomy of Vision Mamba, a state space model-based architecture that excels in long sequence modeling and has potential to outperform Transformers in visual tasks.
Contribution
It offers an in-depth review of Mamba's development, applications in visual domains, and its impact, establishing a taxonomy for future research and applications.
Findings
Mamba demonstrates strong long-range dependency modeling in visual tasks.
Mamba achieves efficient training and inference with linear time complexity.
The survey highlights Mamba's potential to surpass Transformer architectures.
Abstract
State Space Model (SSM) is a mathematical model used to describe and analyze the behavior of dynamic systems. This model has witnessed numerous applications in several fields, including control theory, signal processing, economics and machine learning. In the field of deep learning, state space models are used to process sequence data, such as time series analysis, natural language processing (NLP) and video understanding. By mapping sequence data to state space, long-term dependencies in the data can be better captured. In particular, modern SSMs have shown strong representational capabilities in NLP, especially in long sequence modeling, while maintaining linear time complexity. Notably, based on the latest state-space models, Mamba merges time-varying parameters into SSMs and formulates a hardware-aware algorithm for efficient training and inference. Given its impressive efficiency…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGlobal Maritime and Colonial Histories
MethodsAttention Is All You Need · Dropout · Label Smoothing · Residual Connection · Softmax · Position-Wise Feed-Forward Layer · Absolute Position Encodings · Linear Layer · Byte Pair Encoding · Adam
