mlsanityData to 14 Oct 2026

DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition

arXiv 2503.14867 ↗First posted 19 Mar 2025cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Recently, Vision Graph Neural Network (ViG) has gained considerable attention in computer vision. Despite its groundbreaking innovation, Vision Graph Neural Network encounters key issues including the quadratic computational complexity caused by its K-Nearest Neighbor (KNN) graph construction and the limitation of pairwise relations of normal graphs. To address the aforementioned challenges, we propose a novel vision architecture, termed Dilated Vision HyperGraph Neural Network (DVHGNN), which is designed to leverage multi-scale hypergraph to efficiently capture high-order correlations among objects. Specifically, the proposed method tailors Clustering and Dilated HyperGraph Construction (DHGC) to adaptively capture multi-scale dependencies among the data samples. Furthermore, a dynamic hypergraph convolution mechanism is proposed to facilitate adaptive feature exchange and fusion at the hypergraph level. Extensive qualitative and quantitative evaluations of the benchmark image datasets demonstrate that the proposed DVHGNN significantly outperforms the state-of-the-art vision backbones. For instance, our DVHGNN-S achieves an impressive top-1 accuracy of 83.1% on ImageNet-1K, surpassing ViG-S by +1.0% and ViHGNN-S by +0.6%.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 48 of its 68 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

48 of 68 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  8. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  9. 2017Mask R-CNNcited by 7,277
  10. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  11. 2017Inductive Representation Learning on Large Graphscited by 6,320
  12. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
36 more
  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  2. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  3. 2018How Powerful are Graph Neural Networks?cited by 4,393
  4. 2014Going Deeper with Convolutionscited by 4,241
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  6. 2022A ConvNet for the 2020scited by 3,579
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  9. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  10. 2017Deformable Convolutional Networkscited by 1,488
  11. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  12. 2017Random Erasing Data Augmentationcited by 1,239
  13. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  14. 2016Deep Networks with Stochastic Depthcited by 979
  15. 2024VMamba: Visual State Space Modelcited by 969
  16. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  17. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  18. 2019Panoptic Feature Pyramid Networkscited by 645
  19. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  20. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  21. 2022Vision Transformer with Deformable Attentioncited by 295
  22. 2019Learning Discrete Structures for Graph Neural Networkscited by 231
  23. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  24. 2018Exploring Visual Relationship for Image Captioningcited by 215
  25. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
  26. 2022Vision GNN: An Image is Worth Graph of Nodescited by 186
  27. 2023FLatten Transformer: Vision Transformer using Focused Linear Attentioncited by 171
  28. 2021UniGNN: a Unified Framework for Graph and Hypergraph Neural Networkscited by 130
  29. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  30. 2023InceptionNeXt: When Inception Meets ConvNeXtcited by 86
  31. 2020HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphscited by 54
  32. 2023Image as Set of Pointscited by 43
  33. 2023Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attentioncited by 38
  34. 2021Learnable Hypergraph Laplacian for Hypergraph Learningcited by 16
  35. 2024Neural Clustering based Visual Representation Learningcited by 12
  36. 2023ClusterFormer: Clustering As A Universal Visual Learnercited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memorycited by 6
  2. 2025EHGCN: Hierarchical Euclidean-Hyperbolic Fusion via Motion-Aware GCN for Hybrid Event Stream Perceptioncited by 1
  3. 2025AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNscited by 1
  4. 2026HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detectioncited by 0
  5. 2026GraphLeap: Decoupling Graph Construction and Convolution for Vision GNN Acceleration on FPGAcited by 0
  6. 2026EMERGE: Resolution-Agnostic Point Cloud Generation with Equivariant Graph-Based Diffusioncited by 0