Can Graphs Help Vision SSMs See Better?

• URL: http://arxiv.org/abs/2605.11300v1
• Date: Mon, 11 May 2026 22:40:37 GMT
• Title: Can Graphs Help Vision SSMs See Better?
• Abstract summary: We introduce textbfGraphScan, a graph-induced dynamic scanning operator for Vision SSMs.<n>For each token, GraphScan constructs a spatially bounded local graph, learns feature-conditioned affinities with relative positional bias, and produces the output token.<n>Our analysis shows that GraphScan induces interpretable displacement fields over the token lattice, providing a semantic and spatially grounded view of dynamic scanning.
• Score: 8.221734233588085
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision state space models inherit the efficiency and long-range modeling ability of Mamba-style selective scans. However, their performance depends critically on the representation of two-dimensional visual features as one-dimensional token sequences. Existing scan operators range from predefined geometric traversals to dynamic coordinate-based samplers that reroute tokens through predicted offsets and interpolation. While effective, these mechanisms primarily adapt paths or sampling locations, rather than explicitly modeling which local patches should exchange information before global state-space mixing. This motivates a simple question: \emph{can graphs help vision state space models see better?} We introduce \textbf{GraphScan}, a graph-induced dynamic scanning operator for Vision SSMs. For each token, GraphScan constructs a spatially bounded local graph, learns feature-conditioned affinities with relative positional bias, and produces the output token by one-step message passing over its semantic neighborhood. The resulting tokens are locally grounded before being processed by the selective SSM for global aggregation. GraphScan preserves token count and linear scaling in image size, while replacing coordinate-conditioned interpolation with feature-conditioned semantic routing. Integrated into a hierarchical backbone, \textbf{GraphScan-Mamba} achieves state-of-the-art performance among Vision SSMs across image classification, object detection, instance segmentation, and semantic segmentation, with modest computational overhead. Our analysis further shows that GraphScan induces interpretable displacement fields over the token lattice, providing a semantic and spatially grounded view of dynamic scanning. These results suggest that future Vision SSMs should treat scanning not merely as geometric serialization, but as learned local semantic routing before global state-space modeling.

Related papers

• DAMamba: Vision State Space Model with Dynamic Adaptive Scan [51.81060691414399]
  State space models (SSMs) have recently garnered significant attention in computer vision.<n>We propose Dynamic Adaptive Scan (DAS), a data-driven method that adaptively allocates scanning orders and regions.<n>Based on DAS, we propose the vision backbone DAMamba, which significantly outperforms current state-of-the-art vision Mamba models in vision tasks.
  arXiv  Detail & Related papers  (2025-02-18T08:12:47Z)
• Hierarchical Graph Interaction Transformer with Dynamic Token Clustering for Camouflaged Object Detection [57.883265488038134]
  We propose a hierarchical graph interaction network termed HGINet for camouflaged object detection. The network is capable of discovering imperceptible objects via effective graph interaction among the hierarchical tokenized features. Our experiments demonstrate the superior performance of HGINet compared to existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-27T12:53:25Z)
• DynamicGlue: Epipolar and Time-Informed Data Association in Dynamic Environments using Graph Neural Networks [13.42760841894735]
  We propose a graph neural network-based sparse feature matching network to perform robust matching under challenging conditions. We employ a similar scheme of attentional aggregation over graph edges to enhance keypoint representations as state-of-the-art feature-matching networks. A series of experiments show the superior performance of our network as it excludes keypoints on moving objects compared to state-of-the-art feature matching networks.
  arXiv  Detail & Related papers  (2024-03-17T23:23:40Z)
• Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis [11.353826466710398]
  We propose a novel dynamic graph representation algorithm that conceptualizes WSIs as a form of the knowledge graph structure. Specifically, we dynamically construct neighbors and directed edge embeddings based on the head and tail relationships between instances. Our end-to-end graph representation learning approach has outperformed the state-of-the-art WSI analysis methods on three TCGA benchmark datasets and in-house test sets.
  arXiv  Detail & Related papers  (2024-03-12T14:58:51Z)
• Graph Information Bottleneck for Remote Sensing Segmentation [8.879224757610368]
  This paper treats images as graph structures and introduces a simple contrastive vision GNN architecture for remote sensing segmentation. Specifically, we construct a node-masked and edge-masked graph view to obtain an optimal graph structure representation. We replace the convolutional module in UNet with the SC-ViG module to complete the segmentation and classification tasks.
  arXiv  Detail & Related papers  (2023-12-05T07:23:22Z)
• Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation [38.09501948846373]
  We introduce the topological adjacency relationship among the tokens, emphasizing their relative position information. We incorporate these graphs into the pre-trained language model by adding graph neural network layers on top of the language model embeddings. Experiments on two benchmark datasets show that LAGER significantly outperforms strong baselines under different few-shot settings.
  arXiv  Detail & Related papers  (2023-05-24T07:34:33Z)
• Location-Aware Self-Supervised Transformers [74.76585889813207]
  We propose to pretrain networks for semantic segmentation by predicting the relative location of image parts. We control the difficulty of the task by masking a subset of the reference patch features visible to those of the query. Our experiments show that this location-aware pretraining leads to representations that transfer competitively to several challenging semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-12-05T16:24:29Z)
• Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
  Modelling long-range dependencies is critical for scene understanding tasks in computer vision. A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive. We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
  arXiv  Detail & Related papers  (2022-09-20T14:41:37Z)
• Learning Hierarchical Graph Representation for Image Manipulation Detection [50.04902159383709]
  The objective of image manipulation detection is to identify and locate the manipulated regions in the images. Recent approaches mostly adopt the sophisticated Convolutional Neural Networks (CNNs) to capture the tampering artifacts left in the images. We propose a hierarchical Graph Convolutional Network (HGCN-Net), which consists of two parallel branches.
  arXiv  Detail & Related papers  (2022-01-15T01:54:25Z)
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
  This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
  arXiv  Detail & Related papers  (2020-12-09T12:40:13Z)

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.