Saved in:
Bibliographic Details
Main Authors: Zhao, Feiyue, Zhang, Zhichao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.11497
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908491070832640
author Zhao, Feiyue
Zhang, Zhichao
author_facet Zhao, Feiyue
Zhang, Zhichao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11497
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
Zhao, Feiyue
Zhang, Zhichao
Computer Vision and Pattern Recognition
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.
title Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.11497