BriefGPT.xyz
Mar, 2021
DER:动态可扩展表示用于类增量学习
DER: Dynamically Expandable Representation for Class Incremental Learning
HTML
PDF
Shipeng Yan, Jiangwei Xie, Xuming He
TL;DR
提出了一种新颖的、两阶段的学习方法,利用动态可扩展表示进行更有效的概念建模,在三个类别的增量学习基准测试中,该方法始终表现出比其他方法更好很大的优势。
Abstract
We address the problem of class
incremental learning
, which is a core step towards achieving adaptive vision intelligence. In particular, we consider the task setting of
incremental learning
with
→