BriefGPT.xyz
Oct, 2019
自监督学习:逐个样本学习泛化能力
Learning to Generalize One Sample at a Time with Self-Supervision
HTML
PDF
Antonio D'Innocente, Silvia Bucci, Tatiana Tommasi, Barbara Caputo
TL;DR
本文探讨了如何在不增加过多数据注释的情况下,利用自监督学习来实现领域泛化和适应性,结果表明该方法在三种不同的情景下有效。
Abstract
Although
deep networks
have significantly increased the performance of
visual recognition
methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applicat
→