Training Convolutional Networks with Noisy Labels
作者： Manohar Paluri , Sainbayar Sukhbaatar , Joan Bruna , Rob Fergus , Lubomir Bourdev
DOI:
关键词:
摘要: … manual annotation of the data is impractical; instead our … on several datasets, including large scale experiments on the … Therefore, we start updating Q along with the rest of the network, …
arxiv.org参考文章(31)
Jakramate Bootkrajang, Ata Kabán, Label-Noise robust logistic regression and its applications european conference on machine learning. pp. 143- 158 ,(2012) , 10.1007/978-3-642-33460-3_15
Ronan Collobert, Clément Farabet, Koray Kavukcuoglu, Torch7: A Matlab-like Environment for Machine Learning neural information processing systems. ,(2011)
Ricardo Barandela, Eduardo Gasca, Decontamination of Training Samples for Supervised Pattern Recognition Methods Lecture Notes in Computer Science. pp. 621- 630 ,(2000) , 10.1007/3-540-44522-6_64
Bernhard Schölkopf, Neil D. Lawrence, Estimating a Kernel Fisher Discriminant in the Presence of Label Noise international conference on machine learning. pp. 306- 313 ,(2001)
Vladimir Vapnik, Isabelle Guyon, Nada Matic, Discovering informative patterns and data cleaning knowledge discovery and data mining. pp. 181- 203 ,(1996)
Carla E. Brodley, Mark A. Friedl, Identifying mislabeled training data Journal of Artificial Intelligence Research. ,vol. 11, pp. 131- 167 ,(1999) , 10.1613/JAIR.606
Karen Simonyan, Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition computer vision and pattern recognition. ,(2014)
David F. Nettleton, Albert Orriols-Puig, Albert Fornells, A study of the effect of different types of noise on the precision of supervised learning techniques Artificial Intelligence Review. ,vol. 33, pp. 275- 306 ,(2010) , 10.1007/S10462-010-9156-Z
Xingquan Zhu, Xindong Wu, Class noise vs. attribute noise: a quantitative study of their impacts Artificial Intelligence Review. ,vol. 22, pp. 177- 210 ,(2003) , 10.1007/S10462-004-0751-8
Xiaojin Zhu, John Lafferty, Harmonic mixtures Proceedings of the 22nd international conference on Machine learning - ICML '05. pp. 1052- 1059 ,(2005) , 10.1145/1102351.1102484