GraphTEN: Graph Enhanced Texture Encoding Network

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Peng, Bo, Chen, Jintao, Yao, Mufeng, Zhang, Chenhao, Zhang, Jianghui, Chi, Mingmin, Tao, Jiang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908273178836992
author Peng, Bo
Chen, Jintao
Yao, Mufeng
Zhang, Chenhao
Zhang, Jianghui
Chi, Mingmin
Tao, Jiang
author_facet Peng, Bo
Chen, Jintao
Yao, Mufeng
Zhang, Chenhao
Zhang, Jianghui
Chi, Mingmin
Tao, Jiang
contents Texture recognition is a fundamental problem in computer vision and pattern recognition. Recent progress leverages feature aggregation into discriminative descriptions based on convolutional neural networks (CNNs). However, modeling non-local context relations through visual primitives remains challenging due to the variability and randomness of texture primitives in spatial distributions. In this paper, we propose a graph-enhanced texture encoding network (GraphTEN) designed to capture both local and global features of texture primitives. GraphTEN models global associations through fully connected graphs and captures cross-scale dependencies of texture primitives via bipartite graphs. Additionally, we introduce a patch encoding module that utilizes a codebook to achieve an orderless representation of texture by encoding multi-scale patch features into a unified feature space. The proposed GraphTEN achieves superior performance compared to state-of-the-art methods across five publicly available datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13991
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GraphTEN: Graph Enhanced Texture Encoding Network
Peng, Bo
Chen, Jintao
Yao, Mufeng
Zhang, Chenhao
Zhang, Jianghui
Chi, Mingmin
Tao, Jiang
Computer Vision and Pattern Recognition
Artificial Intelligence
68T45
I.2.10; I.4.7
Texture recognition is a fundamental problem in computer vision and pattern recognition. Recent progress leverages feature aggregation into discriminative descriptions based on convolutional neural networks (CNNs). However, modeling non-local context relations through visual primitives remains challenging due to the variability and randomness of texture primitives in spatial distributions. In this paper, we propose a graph-enhanced texture encoding network (GraphTEN) designed to capture both local and global features of texture primitives. GraphTEN models global associations through fully connected graphs and captures cross-scale dependencies of texture primitives via bipartite graphs. Additionally, we introduce a patch encoding module that utilizes a codebook to achieve an orderless representation of texture by encoding multi-scale patch features into a unified feature space. The proposed GraphTEN achieves superior performance compared to state-of-the-art methods across five publicly available datasets.
title GraphTEN: Graph Enhanced Texture Encoding Network
topic Computer Vision and Pattern Recognition
Artificial Intelligence
68T45
I.2.10; I.4.7
url https://arxiv.org/abs/2503.13991