VMamba: Visual State Space Model
This work addresses the need for efficient vision models for computer vision applications, representing a novel method for a known bottleneck.
The paper tackles the challenge of designing computationally efficient network architectures in computer vision by adapting Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity, achieving promising performance across diverse visual perception tasks with superior input scaling efficiency compared to existing benchmarks.
Designing computationally efficient network architectures remains an ongoing necessity in computer vision. In this paper, we adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity. At the core of VMamba is a stack of Visual State-Space (VSS) blocks with the 2D Selective Scan (SS2D) module. By traversing along four scanning routes, SS2D bridges the gap between the ordered nature of 1D selective scan and the non-sequential structure of 2D vision data, which facilitates the collection of contextual information from various sources and perspectives. Based on the VSS blocks, we develop a family of VMamba architectures and accelerate them through a succession of architectural and implementation enhancements. Extensive experiments demonstrate VMamba's promising performance across diverse visual perception tasks, highlighting its superior input scaling efficiency compared to existing benchmark models. Source code is available at https://github.com/MzeroMiko/VMamba.