BriefGPT.xyz
Mar, 2020
自监督预训练对视觉任务有多大用处?
How Useful is Self-Supervised Pretraining for Visual Tasks?
HTML
PDF
Alejandro Newell, Jia Deng
TL;DR
研究人员对自监督预训练算法在视觉领域中的实用性进行了评估,发现可用标签数量的增加以及下游任务和训练数据属性的变化都会影响其效用,而线性评估与精调性能之间没有相关性。
Abstract
Recent advances have spurred incredible progress in
self-supervised
pretraining
for
vision
. We investigate what factors may play a role in
→