# A Survey on Mamba Architecture for Vision Applications

Source: [A Survey on Mamba Architecture for Vision Applications](<https://www.sota2.com/research/paper/68fa76ef1e209131cea700e0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:06:07.870Z

Authors: Fady Ibrahim, Guangjun Liu, Guanghui Wang

Published: 2025-02-11T00:59:30.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.07161>)

[PDF](<https://arxiv.org/pdf/2502.07161.pdf>)