paper-with-me

Papers

VMamba: Visual State Space Model

2024-01-18 · Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, YaoWei Wang, Qixiang Ye, Jianbin Jiao, Yunfan Liu

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.

📄 PDF Abstract BibTeX arXiv:2401.10166

Code (13)

mzeromiko/vmamba 공식 구현 pytorch
AmazingDay1/TAME pytorch
chenhongruixuan/mambacd
hunto/localmamba pytorch
longshaocong/dgmamba pytorch
piskovskyi/fMRI-VisionMamba pytorch
raytrun/mamba-clip pytorch
weitunglin/pixmamba pytorch
weiwang31/icemamba pytorch
yuhengsss/msvmamba pytorch
zs1314/microscopic-mamba pytorch
zs1314/octamamba pytorch
zs1314/skinmamba pytorch

Tasks

Computational EfficiencyLanguage ModelingLanguage ModellingMambamodelRepresentation Learning

Similar Papers 제목 키워드 기반

VMambaMorph: a Multi-Modality Deformable Image Registration Framework based on Visual State Space Model with Cross-Scan Module

2024-04-07 · Ziyang Wang, Jian-Qing Zheng, Chao Ma, Tao Guo

Image registration, a critical process in medical imaging, involves aligning different sets of medical imaging data into a single unified coordinate system. Deep learning networks, such as the Convolutional Neural Networ…

Image Registration

BadScan: An Architectural Backdoor Attack on Visual State Space Models

2024-11-26 · Om Suhas Deshmukh, Sankalp Nagaonkar, Achyut Mani Tripathi, Ashish Mishra

The newly introduced Visual State Space Model (VMamba), which employs \textit{State Space Mechanisms} (SSM) to interpret images as sequences of patches, has shown exceptional performance compared to Vision Transformers (…

Backdoor Attackimage-classificationImage ClassificationState Space Models+1

EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba

2024-03-15 · Xiaohuan Pei, Tao Huang, Chang Xu

Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction compromise resolution while Transformers offer …

Language ModelingLanguage ModellingMambaState Space Models

VMambaCC: A Visual State Space Model for Crowd Counting

2024-05-07 · Hao-Yuan Ma, Li Zhang, Shuai Shi

As a deep learning model, Visual Mamba (VMamba) has a low computational complexity and a global receptive field, which has been successful applied to image classification and detection. To extend its applications, we app…

Crowd Countingimage-classificationImage ClassificationMamba

HRVMamba: High-Resolution Visual State Space Model for Dense Prediction

2024-10-04 · Hao Zhang, Yongqiang Ma, Wenqi Shao, Ping Luo 외

Recently, State Space Models (SSMs) with efficient hardware-aware designs, i.e., Mamba, have demonstrated significant potential in computer vision tasks due to their linear computational complexity with respect to token …

Inductive BiasMambaPose EstimationSemantic Segmentation+1