用多尺度稀疏超图提升视觉识别效率，精度超现有模型。
DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition
- 通过聚类与稀疏超图构建，捕捉多尺度对象关系。
- 在ImageNet-1K上达83.1%准确率，优于ViG-S和ViHGNN-S。
- 适合追求高效高精度视觉模型的研究者使用。
视觉图神经网络（ViG）在计算机视觉中受到广泛关注。尽管创新突出，但其因K近邻（KNN）图构建导致二次计算复杂度，且普通图的成对关系受限。为此，本文提出新型视觉架构——稀疏视觉超图神经网络（DVHGNN），利用多尺度超图高效捕捉对象间的高阶关联。具体而言，设计了聚类与稀疏超图构建（DHGC）方法，自适应捕获数据样本间的多尺度依赖；并提出动态超图卷积机制，在超图层级实现自适应特征交换与融合。在基准图像数据集上的大量定性与定量评估表明，所提DVHGNN显著优于当前最优视觉主干网络。例如，DVHGNN-S在ImageNet-1K上达到83.1%的顶级准确率，较ViG-S提升+1.0%，较ViHGNN-S提升+0.6%。
原文摘要 · Abstract (English)
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%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。