Learn Faster and Forget Slower via Fast and Stable Task Adaptation

Farshid Varno
Farshid Varno
Lucas May Petry
Lucas May Petry
Lisa Di Jorio
Lisa Di Jorio
被引用0|浏览5

摘要

Training Deep Neural Networks (DNNs) is still highly time-consuming and compute-intensive. It has been shown that adapting a pretrained model may significantly accelerate this process. With a focus on classification, we show that current fine-tuning techniques make the pretrained models catastrophically forget the transferred knowledge ...更多

代码

数据

ZH
下载 PDF 全文
引用
您的评分 :
0

 

标签
评论