QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model

• URL: http://arxiv.org/abs/2410.06806v2
• Date: Thu, 10 Oct 2024 06:19:20 GMT
• Title: QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model
• Authors: Fei Xie, Weijia Zhang, Zhongdao Wang, Chao Ma,
• Abstract summary: New vision Mamba model, coined QuadMamba, captures local dependencies of varying granularities via quadtree-based image partition and scan. QuadMamba achieves state-of-the-art performance in various vision tasks, including image classification, object detection, instance segmentation, and semantic segmentation.
• Score: 16.01259690063522
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in State Space Models, notably Mamba, have demonstrated superior performance over the dominant Transformer models, particularly in reducing the computational complexity from quadratic to linear. Yet, difficulties in adapting Mamba from language to vision tasks arise due to the distinct characteristics of visual data, such as the spatial locality and adjacency within images and large variations in information granularity across visual tokens. Existing vision Mamba approaches either flatten tokens into sequences in a raster scan fashion, which breaks the local adjacency of images, or manually partition tokens into windows, which limits their long-range modeling and generalization capabilities. To address these limitations, we present a new vision Mamba model, coined QuadMamba, that effectively captures local dependencies of varying granularities via quadtree-based image partition and scan. Concretely, our lightweight quadtree-based scan module learns to preserve the 2D locality of spatial regions within learned window quadrants. The module estimates the locality score of each token from their features, before adaptively partitioning tokens into window quadrants. An omnidirectional window shifting scheme is also introduced to capture more intact and informative features across different local regions. To make the discretized quadtree partition end-to-end trainable, we further devise a sequence masking strategy based on Gumbel-Softmax and its straight-through gradient estimator. Extensive experiments demonstrate that QuadMamba achieves state-of-the-art performance in various vision tasks, including image classification, object detection, instance segmentation, and semantic segmentation. The code is in https://github.com/VISION-SJTU/QuadMamba.

Related papers

• Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion [46.82975707531064]
  Selective state space models (SSMs) excel at capturing long-range dependencies in 1D sequential data. We propose Spatial-Mamba, a novel approach that establishes neighborhood connectivity directly in the state space. We show that Spatial-Mamba, even with a single scan, attains or surpasses the state-of-the-art SSM-based models in image classification, detection and segmentation.
  arXiv  Detail & Related papers  (2024-10-19T12:56:58Z)
• 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)
• FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizers [55.2480439325792]
  We propose FUSE, an approach to approximating an adapter layer that maps from one model's textual embedding space to another, even across different tokenizers. We show the efficacy of our approach via multi-objective optimization over vision-language and causal language models for image captioning and sentiment-based image captioning.
  arXiv  Detail & Related papers  (2024-08-09T02:16:37Z)
• A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion [14.293042131263924]
  In image fusion tasks, images from different sources possess distinct characteristics. Mamba, as a state space model, has emerged in the field of natural language processing. Motivated by these challenges, we customize and improve the vision Mamba network designed for the image fusion task.
  arXiv  Detail & Related papers  (2024-04-14T16:09:33Z)
• 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)
• LocalMamba: Visual State Space Model with Windowed Selective Scan [45.00004931200446]
  Key to enhancing Vision Mamba (ViM) lies in optimizing scan directions for sequence modeling. We introduce a novel local scanning strategy that divides images into distinct windows, effectively capturing local dependencies. Our model significantly outperforms Vim-Ti by 3.1% on ImageNet with the same 1.5G FLOPs.
  arXiv  Detail & Related papers  (2024-03-14T12:32:40Z)
• MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection [72.46396769642787]
  We develop a nested structure, Mamba-in-Mamba (MiM-ISTD), for efficient infrared small target detection. MiM-ISTD is $8 times$ faster than the SOTA method and reduces GPU memory usage by 62.2$%$ when testing on $2048 times 2048$ images.
  arXiv  Detail & Related papers  (2024-03-04T15:57:29Z)
• 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)

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.