Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
By: Feiyue Zhao, Zhichao Zhang
Potential Business Impact:
Helps computers see objects better in pictures.
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.
Similar Papers
Hierarchical Frequency-Decomposition Graph Neural Networks for Road Network Representation Learning
Machine Learning (CS)
Improves traffic flow by understanding road patterns.
Brain-HGCN: A Hyperbolic Graph Convolutional Network for Brain Functional Network Analysis
CV and Pattern Recognition
Helps doctors find brain problems from brain scans.
Multi-Modal Feature Fusion for Spatial Morphology Analysis of Traditional Villages via Hierarchical Graph Neural Networks
CV and Pattern Recognition
Helps computers understand how villages change over time.