Scholarlink

This study explores the use of Graph Neural Networks (GNNs) for image semantic segmentation, focusing on super-pixel-based approaches to ensure reasonable use of computational power. We evaluate various GNN modules on synthetic datasets of varying complexity, using a hierarchical GNN architecture inspired by U-Net. Our results show that GNNs with attention mechanisms perform well in handling noisy data and reconstructing complex shapes, sometimes surpassing traditional Convolutional Neural Networks (CNNs). Future research will assess the efficacy of this approach on real-world datasets.

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

Hierarchical Super-Pixels Graph Neural Networks for Image Semantic Segmentation

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Xavier Hoarau,
  • Julien Mille,
  • Hugo Raguet,
  • Romain Raveaux

摘要

This study explores the use of Graph Neural Networks (GNNs) for image semantic segmentation, focusing on super-pixel-based approaches to ensure reasonable use of computational power. We evaluate various GNN modules on synthetic datasets of varying complexity, using a hierarchical GNN architecture inspired by U-Net. Our results show that GNNs with attention mechanisms perform well in handling noisy data and reconstructing complex shapes, sometimes surpassing traditional Convolutional Neural Networks (CNNs). Future research will assess the efficacy of this approach on real-world datasets.