AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2021)

被引用0|浏览11
下载 PDF 全文
引用

摘要

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns from different visual domains, it tends to forget the past ones in favor of the most recent. In th...更多

代码

数据

作者
Riccardo Volpi
Riccardo Volpi
Diane Larlus
Diane Larlus
Grégory Rogez
Grégory Rogez
您的评分 :
0

 

标签
评论
小科