A Survey on Visual Mamba

Abstract

State space models (SSM) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently shown significant potential in long-sequence modeling. Since the complexity of transformers’ self-attention mechanism is quadratic with image size, as well as increasing computational demands, researchers are currently exploring how to adapt Mamba for computer vision tasks. This paper is the first comprehensive survey that aims to provide an in-depth analysis of Mamba models within the domain of computer vision. It begins by exploring the foundational concepts contributing to Mamba’s success, including the SSM framework, selection mechanisms, and hardware-aware design. Then, we review these vision Mamba models by categorizing them into foundational models and those enhanced with techniques including convolution, recurrence, and attention to improve their sophistication. Furthermore, we investigate the widespread applications of Mamba in vision tasks, which include their use as a backbone in various levels of vision processing. This encompasses general visual tasks, medical visual tasks (e.g., 2D/3D segmentation, classification, image registration, etc.), and remote sensing visual tasks. In particular, we introduce general visual tasks from two levels: high/mid-level vision (e.g., object detection, segmentation, video classification, etc.) and low-level vision (e.g., image super-resolution, image restoration, visual generation, etc.). We hope this endeavor will spark additional interest within the community to address current challenges and further apply Mamba models in computer vision.