用图结构增强CNN的局部与全局感知能力，提升视觉识别效果。
Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
- 构建双层图结构，捕捉局部依赖和全局语义关系
- 自适应调频模块平衡高低频信号，保留纹理细节
- 轻量级设计可无缝嵌入主流CNN模型，适合多任务应用
卷积神经网络（CNN）在视觉识别中表现优异，但其对规则网格结构的依赖限制了对图像中复杂拓扑关系和非局部语义的建模能力。为此，本文提出分层图特征增强（HGFE）框架，将基于图的推理机制融入CNN，以提升结构感知与特征表示能力。HGFE构建两个互补的图结构层次：窗内图卷积用于捕捉局部空间依赖，窗间超结点交互用于建模全局语义关系。此外，引入自适应频率调制模块，动态调节低频与高频信号传播，在保留关键边缘和纹理信息的同时缓解过度平滑问题。所提HGFE模块轻量、端到端可训练，可无缝集成至标准CNN主干网络。在CIFAR-100（分类）、PASCAL VOC和VisDrone（检测），以及CrackSeg和CarParts（分割）上的大量实验验证了其在提升结构表征与整体识别性能方面的有效性。
原文摘要 · Abstract (English)
Convolutional neural networks (CNNs) have demonstrated strong performance in visual recognition tasks, but their inherent reliance on regular grid structures limits their capacity to model complex topological relationships and non-local semantics within images. To address this limita tion, we propose the hierarchical graph feature enhancement (HGFE), a novel framework that integrates graph-based rea soning into CNNs to enhance both structural awareness and feature representation. HGFE builds two complementary levels of graph structures: intra-window graph convolution to cap ture local spatial dependencies and inter-window supernode interactions to model global semantic relationships. Moreover, we introduce an adaptive frequency modulation module that dynamically balances low-frequency and high-frequency signal propagation, preserving critical edge and texture information while mitigating over-smoothing. The proposed HGFE module is lightweight, end-to-end trainable, and can be seamlessly integrated into standard CNN backbone networks. Extensive experiments on CIFAR-100 (classification), PASCAL VOC, and VisDrone (detection), as well as CrackSeg and CarParts (segmentation), validated the effectiveness of the HGFE in improving structural representation and enhancing overall recognition performance.
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。