使Grad-CAM

Iban Berganzo-Besga1,2,3, Hector A Orengo1,3,4, Felipe Lumbreras5,6

  • 1Computational Social Sciences and Humanities Department, Barcelona Supercomputing Center (BSC-CNS), Barcelona 08034, Spain.

Annals of botany
|May 30, 2025
PubMed
概括

像Guided Grad-CAM这样的视觉解释器在深度学习模型中提高了识别植物植物体的透明度. 这项研究验证了传统的识别模式,并揭示了新的属性特征,推进了计算考古学的实践.