Auxiliary Image Regularization for Deep CNNs with Noisy Labels
Lists
Only you see this
Abstract
Precisely-labeled data sets with sufficient amount of samples are very important for training deep convolutional neural networks (CNNs). However, many of the available real-world data sets contain erroneously labeled samples and those errors substantially hinder the learning of very accurate CNN models. In this work, we consider the problem of training a deep CNN model for image classification with mislabeled training samples - an issue that is common in real image data sets with tags supplied by amateur users. To solve this problem, we propose an auxiliary image regularization technique, optimized by the stochastic Alternating Direction Method of Multipliers (ADMM) algorithm, that automatically exploits the mutual context information among training images and encourages the model to select reliable images to robustify the learning process. Comprehensive experiments on benchmark data sets clearly demonstrate our proposed regularized CNN model is resistant to label noise in training data.
BibTeX
@inproceedings{azadi2016auxiliary,
author = {Samaneh Azadi and Jiashi Feng and Stefanie Jegelka and Trevor Darrell},
title = {{Auxiliary Image Regularization for Deep CNNs with Noisy Labels}},
booktitle = {International Conference on Learning Representations},
year = {2016},
url = {http://arxiv.org/abs/1511.07069},
}Loading related content...