BriefGPT.xyz
Jul, 2021
使用线性探针交叉任务网格解释CNN模型对视网膜图像的预测
Using a Cross-Task Grid of Linear Probes to Interpret CNN Model Predictions On Retinal Images
HTML
PDF
Katy Blumer, Subhashini Venugopalan, Michael P. Brenner, Jon Kleinberg
TL;DR
通过线性探针技术,我们对英国生物库的视网膜图像数据集进行了分析,发现中层神经网络表示更有泛化性,并且有些目标任务的预测与源任务无关,另一些目标任务的预测与与其相关的源任务训练的嵌入效果更好。
Abstract
We analyze a dataset of
retinal images
using
linear probes
: linear regression models trained on some "target" task, using embeddings from a deep convolutional (CNN) model trained on some "source" task as input. W
→