训练深度判别神经网络对抗标签噪声的鲁棒性

May, 2017

训练深度判别神经网络对抗标签噪声的鲁棒性

Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks

Arash Vahdat

TL;DR该论文提出了一种基于无标签干扰数据集训练深度卷积神经网络的新型框架，并使用一个无向图模型来描述干净和嘈杂标签之间的关系，在监督学习过程中学习这个模型。该模型在图像标注问题上应用，并在 CIFAR-10 和 MS COCO 数据集上展示出有效的标注效果和在训练中实现了减少标签噪声的效果。

Abstract

Collecting large training datasets, annotated with high quality labels, is a costly process. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets. The