BriefGPT.xyz
Mar, 2019
利用野外非标记数据克服灾难性遗忘
Incremental Learning with Unlabeled Data in the Wild
HTML
PDF
Kibok Lee, Kimin Lee, Jinwoo Shin, Honglak Lee
TL;DR
本文介绍了一种通过利用大量外部未标记数据集来缓解深度神经网络遗忘现象的类增量学习方法，该方法在各种数据集上均显示出优越性能，尤其是在存在大规模未标记数据时更为显著
Abstract
deep neural networks
are known to suffer from
catastrophic forgetting
in class-
incremental learning
, where the performance on previous tas
→