Scholarlink

<p><b>Abstract</b></p><p>Existing Transformer-based models for fine-grained image classification often struggle to explicitly model the granular hierarchical relationships among multi-scale features and perform adaptive fusion. This limitation leads to the insufficient utilization of discriminative features. Inspired by granular computing theory, this paper proposes a Multi-Granularity Collaborative Network (MGCN-FGIC) that integrates core operations—including granulation, enhancement, alignment, and fusion—into a deep learning framework. Specifically, the network reorganizes and enhances backbone features via a Granule-aware Enhancer and achieves adaptive collaborative fusion of cross-granularity information using a Granule Fusion Neck. Furthermore, a Dynamic Hard Example Mining mechanism is designed to trigger multi-granularity supervision based on sample difficulty, thereby improving discriminative ability for challenging examples. The proposed method achieves classification accuracies of 92.95%, 93.56%, and 91.89% on three public datasets: CUB-200–2011, Stanford Cars, and Stanford Dogs, respectively. Experimental results demonstrate that MGCN-FGIC significantly enhances the ability to distinguish subtle visual differences without notably increasing inference complexity, highlighting the potential of granular computing in fine-grained visual tasks.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A fine-grained image classification method based on MGCN-FGIC

  • 期刊论文

  • 发表日期：

    2026年2月28日

查看全文
  • Chunying Zhang,
  • Qingda Zhang,
  • Jing Ren,
  • Tao Xue,
  • Jinghong Fu

摘要

Abstract

Existing Transformer-based models for fine-grained image classification often struggle to explicitly model the granular hierarchical relationships among multi-scale features and perform adaptive fusion. This limitation leads to the insufficient utilization of discriminative features. Inspired by granular computing theory, this paper proposes a Multi-Granularity Collaborative Network (MGCN-FGIC) that integrates core operations—including granulation, enhancement, alignment, and fusion—into a deep learning framework. Specifically, the network reorganizes and enhances backbone features via a Granule-aware Enhancer and achieves adaptive collaborative fusion of cross-granularity information using a Granule Fusion Neck. Furthermore, a Dynamic Hard Example Mining mechanism is designed to trigger multi-granularity supervision based on sample difficulty, thereby improving discriminative ability for challenging examples. The proposed method achieves classification accuracies of 92.95%, 93.56%, and 91.89% on three public datasets: CUB-200–2011, Stanford Cars, and Stanford Dogs, respectively. Experimental results demonstrate that MGCN-FGIC significantly enhances the ability to distinguish subtle visual differences without notably increasing inference complexity, highlighting the potential of granular computing in fine-grained visual tasks.