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.
@article{arxiv.2503.13991,
title = {GraphTEN: Graph Enhanced Texture Encoding Network},
author = {Bo Peng and Jintao Chen and Mufeng Yao and Chenhao Zhang and Jianghui Zhang and Mingmin Chi and Jiang Tao},
journal= {arXiv preprint arXiv:2503.13991},
year = {2025}
}