BriefGPT.xyz
May, 2019
图像分类的十亿级半监督学习
Billion-scale semi-supervised learning for image classification
HTML
PDF
I. Zeki Yalniz, Hervé Jégou, Kan Chen, Manohar Paluri, Dhruv Mahajan
TL;DR
通过利用大量未标记的图像，本文提出了一种基于师生范式的管道来改善卷积神经网络的性能，并对我们的方法取得成功的因素提供了广泛的分析，从而为图像分类的半监督学习产生高精度模型提出了建议。
Abstract
This paper presents a study of
semi-supervised learning
with large
convolutional networks
. We propose a pipeline, based on a teacher/student paradigm, that leverages a large collection of unlabelled images (up to
→