BriefGPT.xyz
Mar, 2018
学习噪声标签的联合优化框架
Joint Optimization Framework for Learning with Noisy Labels
HTML
PDF
Daiki Tanaka, Daiki Ikami, Toshihiko Yamasaki, Kiyoharu Aizawa
TL;DR
本文提出了一种利用联合优化框架来学习深度神经网络参数和估算真实标签的方法，以克服在噪声标签数据集上进行训练导致性能下降的问题，实验结果表明该方法在解决CIFAR-10噪声数据集和Clothing1M数据集分类问题上优于其他最先进的方法。
Abstract
deep neural networks
(DNNs) trained on large-scale datasets have exhibited significant performance in
image classification
. Many large-scale datasets are collected from websites, however they tend to contain inac
→