Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
- URL: http://arxiv.org/abs/2405.14174v1
- Date: Thu, 23 May 2024 04:59:49 GMT
- Title: Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
- Authors: Yuheng Shi, Minjing Dong, Chang Xu,
- Abstract summary: State Space Models (SSMs) have garnered widespread attention due to their global receptive field and linear complexity.
To improve the performance of SSMs in vision tasks, a multi-scan strategy is widely adopted.
We introduce Multi-Scale Vision Mamba (MSVMamba) to preserve the superiority of SSMs in vision tasks with limited parameters.
- Score: 26.786890883280062
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Despite the significant achievements of Vision Transformers (ViTs) in various vision tasks, they are constrained by the quadratic complexity. Recently, State Space Models (SSMs) have garnered widespread attention due to their global receptive field and linear complexity with respect to the input length, demonstrating substantial potential across fields including natural language processing and computer vision. To improve the performance of SSMs in vision tasks, a multi-scan strategy is widely adopted, which leads to significant redundancy of SSMs. For a better trade-off between efficiency and performance, we analyze the underlying reasons behind the success of the multi-scan strategy, where long-range dependency plays an important role. Based on the analysis, we introduce Multi-Scale Vision Mamba (MSVMamba) to preserve the superiority of SSMs in vision tasks with limited parameters. It employs a multi-scale 2D scanning technique on both original and downsampled feature maps, which not only benefits long-range dependency learning but also reduces computational costs. Additionally, we integrate a Convolutional Feed-Forward Network (ConvFFN) to address the lack of channel mixing. Our experiments demonstrate that MSVMamba is highly competitive, with the MSVMamba-Tiny model achieving 82.8% top-1 accuracy on ImageNet, 46.9% box mAP, and 42.2% instance mAP with the Mask R-CNN framework, 1x training schedule on COCO, and 47.6% mIoU with single-scale testing on ADE20K.Code is available at \url{https://github.com/YuHengsss/MSVMamba}.
Related papers
- Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning [54.19222454702032]
Continual Learning aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowledge.
State Space Models (SSMs) have achieved notable success in computer vision.
We introduce Mamba-CL, a framework that continuously fine-tunes the core SSMs of the large-scale Mamba foundation model.
arXiv Detail & Related papers (2024-11-23T06:36:16Z) - Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution [42.259283231048954]
State Space Models (SSM) have shown strong representation ability in modeling long-range dependency with linear complexity.
We propose a novel Hierarchical Mamba network, namely, Hi-Mamba, for image super-resolution (SR)
arXiv Detail & Related papers (2024-10-14T04:15:04Z) - HRVMamba: High-Resolution Visual State Space Model for Dense Prediction [60.80423207808076]
State Space Models (SSMs) with efficient hardware-aware designs have demonstrated significant potential in computer vision tasks.
These models have been constrained by three key challenges: insufficient inductive bias, long-range forgetting, and low-resolution output representation.
We introduce the Dynamic Visual State Space (DVSS) block, which employs deformable convolution to mitigate the long-range forgetting problem.
We also introduce High-Resolution Visual State Space Model (HRVMamba) based on the DVSS block, which preserves high-resolution representations throughout the entire process.
arXiv Detail & Related papers (2024-10-04T06:19:29Z) - MSVM-UNet: Multi-Scale Vision Mamba UNet for Medical Image Segmentation [3.64388407705261]
We propose a Multi-Scale Vision Mamba UNet model for medical image segmentation, termed MSVM-UNet.
Specifically, by introducing multi-scale convolutions in the VSS blocks, we can more effectively capture and aggregate multi-scale feature representations from the hierarchical features of the VMamba encoder.
arXiv Detail & Related papers (2024-08-25T06:20:28Z) - GroupMamba: Parameter-Efficient and Accurate Group Visual State Space Model [66.35608254724566]
State-space models (SSMs) have showcased effective performance in modeling long-range dependencies with subquadratic complexity.
However, pure SSM-based models still face challenges related to stability and achieving optimal performance on computer vision tasks.
Our paper addresses the challenges of scaling SSM-based models for computer vision, particularly the instability and inefficiency of large model sizes.
arXiv Detail & Related papers (2024-07-18T17:59:58Z) - DVMSR: Distillated Vision Mamba for Efficient Super-Resolution [7.551130027327461]
We propose DVMSR, a novel lightweight Image SR network that incorporates Vision Mamba and a distillation strategy.
Our proposed DVMSR can outperform state-of-the-art efficient SR methods in terms of model parameters.
arXiv Detail & Related papers (2024-05-05T17:34:38Z) - VMamba: Visual State Space Model [92.83984290020891]
VMamba is a vision backbone that works in linear time complexity.
At the core of VMamba lies a stack of Visual State-Space (VSS) blocks with the 2D Selective Scan (SS2D) module.
arXiv Detail & Related papers (2024-01-18T17:55:39Z) - Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model [83.85856356798531]
VistaLLM is a visual system that addresses coarse- and fine-grained vision-language tasks.
It employs a gradient-aware adaptive sampling technique to represent binary segmentation masks as sequences.
We also introduce a novel task, AttCoSeg, which boosts the model's reasoning and grounding capability over multiple input images.
arXiv Detail & Related papers (2023-12-19T18:53:01Z) - Pruning Self-attentions into Convolutional Layers in Single Path [89.55361659622305]
Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks.
We propose Single-Path Vision Transformer pruning (SPViT) to efficiently and automatically compress the pre-trained ViTs.
Our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously.
arXiv Detail & Related papers (2021-11-23T11:35:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.