Dynamic Vision Mamba

• URL: http://arxiv.org/abs/2504.04787v1
• Date: Mon, 07 Apr 2025 07:31:28 GMT
• Title: Dynamic Vision Mamba
• Authors: Mengxuan Wu, Zekai Li, Zhiyuan Liang, Moyang Li, Xuanlei Zhao, Samir Khaki, Zheng Zhu, Xiaojiang Peng, Konstantinos N. Plataniotis, Kai Wang, Wangbo Zhao, Yang You,
• Abstract summary: Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models.<n>For token redundancy, we analytically find that early token pruning methods will result in inconsistency between training and inference.<n>For block redundancy, we allow each image to select SSM blocks dynamically based on an empirical observation that the inference speed of Mamba-based vision models is largely affected by the number of SSM blocks.
• Score: 41.84910346271891
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists in these models, represented by token and block redundancy. For token redundancy, we analytically find that early token pruning methods will result in inconsistency between training and inference or introduce extra computation for inference. Therefore, we customize token pruning to fit the Mamba structure by rearranging the pruned sequence before feeding it into the next Mamba block. For block redundancy, we allow each image to select SSM blocks dynamically based on an empirical observation that the inference speed of Mamba-based vision models is largely affected by the number of SSM blocks. Our proposed method, Dynamic Vision Mamba (DyVM), effectively reduces FLOPs with minor performance drops. We achieve a reduction of 35.2\% FLOPs with only a loss of accuracy of 1.7\% on Vim-S. It also generalizes well across different Mamba vision model architectures and different vision tasks. Our code will be made public.

Related papers

• DefMamba: Deformable Visual State Space Model [65.50381013020248]
  We propose a novel visual foundation model called DefMamba. By combining a deformable scanning(DS) strategy, this model significantly improves its ability to learn image structures and detects changes in object details. Numerous experiments have shown that DefMamba achieves state-of-the-art performance in various visual tasks.
  arXiv  Detail & Related papers  (2025-04-08T08:22:54Z)
• Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging [40.80197280147993]
  We propose a Mamba-inspired Joint Unfolding Network (MiJUN) to overcome the inherent nonlinear and ill-posed characteristics of HSI reconstruction.<n>We introduce an accelerated unfolding network scheme, which reduces the reliance on initial optimization stages.<n>We refine the scanning strategy with Mamba by integrating the tensor mode-$k$ unfolding into the Mamba network.
  arXiv  Detail & Related papers  (2025-01-02T13:56:23Z)
• V2M: Visual 2-Dimensional Mamba for Image Representation Learning [68.51380287151927]
  Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences. Recent studies have attempted to apply Mamba to the visual domain by flattening 2D images into patches and then regarding them as a 1D sequence. We propose a Visual 2-Dimensional Mamba model as a complete solution, which directly processes image tokens in the 2D space.
  arXiv  Detail & Related papers  (2024-10-14T11:11:06Z)
• MambaVision: A Hybrid Mamba-Transformer Vision Backbone [54.965143338206644]
  We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications.<n>We show that equipping the Mamba architecture with self-attention blocks in the final layers greatly improves its capacity to capture long-range spatial dependencies.<n>For classification on the ImageNet-1K dataset, MambaVision variants achieve state-of-the-art (SOTA) performance in terms of both Top-1 accuracy and throughput.
  arXiv  Detail & Related papers  (2024-07-10T23:02:45Z)
• Demystify Mamba in Vision: A Linear Attention Perspective [72.93213667713493]
  Mamba is an effective state space model with linear computation complexity.<n>We show that Mamba shares surprising similarities with linear attention Transformer.<n>We propose a Mamba-Inspired Linear Attention (MILA) model by incorporating the merits of these two key designs into linear attention.
  arXiv  Detail & Related papers  (2024-05-26T15:31:09Z)
• PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition [21.761988930589727]
  PlainMamba is a simple non-hierarchical state space model (SSM) designed for general visual recognition. We adapt the selective scanning process of Mamba to the visual domain, enhancing its ability to learn features from two-dimensional images. Our architecture is designed to be easy to use and easy to scale, formed by stacking identical PlainMamba blocks.
  arXiv  Detail & Related papers  (2024-03-26T13:35:10Z)
• The Hidden Attention of Mamba Models [54.50526986788175]
  The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains. We show that such models can be viewed as attention-driven models. This new perspective enables us to empirically and theoretically compare the underlying mechanisms to that of the self-attention layers in transformers.
  arXiv  Detail & Related papers  (2024-03-03T18:58:21Z)
• BlackMamba: Mixture of Experts for State-Space Models [10.209192169793772]
  State-space models (SSMs) have recently demonstrated competitive performance to transformers at large-scale language modeling benchmarks. MoE models have shown remarkable performance while significantly reducing the compute and latency costs of inference. We present BlackMamba, a novel architecture that combines the Mamba SSM with MoE to obtain the benefits of both.
  arXiv  Detail & Related papers  (2024-02-01T07:15:58Z)
• VMamba: Visual State Space Model [98.0517369083152]
  We adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity.<n>At the core of VMamba is a stack of Visual State-Space (VSS) blocks with the 2D Selective Scan (SS2D) module.
  arXiv  Detail & Related papers  (2024-01-18T17:55:39Z)

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.