:

Dominik Rivoir1, Isabel Funke1, Stefanie Speidel1

  • 1Department of Translational Surgical Oncology, National Center for Tumor Diseases (NCT/UCC Dresden), Fetscherstraße 74, 01307 Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Dresden, Germany; Centre for Tactile Internet with Human-in-the-Loop (CeTI), TUD Dresden University of Technology, Dresden, Germany.

PubMed
概括

批量规范化 (BN) 阻碍了端到端的视频学习,特别是在外科分析中. 从卷积神经网络 (CNN) 中删除BN使得更简单的模型能够通过改善时间上下文利用来实现最先进的结果.

相关概念视频