Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition

TL;DR

This paper introduces HGFE, a hierarchical graph feature enhancement framework with adaptive frequency modulation, integrated into CNNs to improve structural modeling and recognition accuracy across various visual tasks.

Contribution

The paper proposes a novel HGFE framework that combines hierarchical graph reasoning with adaptive frequency modulation to enhance CNNs for visual recognition.

Findings

Improved accuracy on CIFAR-100, PASCAL VOC, and VisDrone datasets.

Effective modeling of local and global image structures.

Lightweight and easily integrable into existing CNNs.

Abstract

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.