Graph Construction on Whole Image Slides Based on Attention and Learnable Threshold

Different from conventional graph sampling methods for reducing graph size, such as thresholding method and merging method of edge and node, AdaptConv, an inventive Transformer-based graph neural network module is proposed. This module can remove redundant edges through dynamic learning while aggreg...

詳細記述

書誌詳細
出版年:Jisuanji gongcheng
第一著者: CHEN Depin, ZHAO Shen, JIAO Yiping, WANG Xiangxue, LÜ Hong, XU Jun
フォーマット: 論文
言語:英語
出版事項: Editorial Office of Computer Engineering 2025-03-01
主題:
オンライン・アクセス:https://www.ecice06.com/fileup/1000-3428/PDF/20250323.pdf

類似資料