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

2025-03-19

AI Summary

Vision Graph Neural Networks (ViG) suffer from quadratic computational complexity and limited capacity to model higher-order semantic dependencies due to their pairwise graph structures. To address these issues, this paper proposes the Multi-Scale Dilated Hypergraph Neural Network (DVHGNN). Our approach introduces three key innovations: (1) an Adaptive Clustering-based Dilated Hypergraph Construction (DHGC) mechanism that significantly reduces KNN-based graph construction overhead; (2) dynamic hypergraph convolution enabling cross-scale, higher-order relational modeling; and (3) multi-scale feature fusion to enhance representation capability. Evaluated on ImageNet-1K, DVHGNN-S achieves 83.1% top-1 accuracy—outperforming ViG-S and ViHGNN-S by 1.0% and 0.6%, respectively—while attaining a superior trade-off between accuracy and computational efficiency.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

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%.

Problem

• Addresses quadratic computational complexity in KNN graph construction.
• Overcomes limitations of pairwise relations in normal graphs.
• Captures high-order correlations efficiently using multi-scale hypergraphs.

Innovation

• Multi-scale hypergraph captures high-order correlations
• Clustering and Dilated HyperGraph Construction adaptively
• Dynamic hypergraph convolution for feature fusion