Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks

Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets that can be obtained cheaply. The problem is formulated using an undirected graphical model that represents the relationship between noisy and clean labels, trained in a semi-supervised setting. In our formulation, the inference over latent clean labels is tractable and is regularized during training using auxiliary sources of information. The proposed model is applied to the image labeling problem and is shown to be effective in labeling unseen images as well as reducing label noise in training on CIFAR-10 and MS COCO datasets.

[1]  Eric Fosler-Lussier,et al.  Backpropagation training for multilayer conditional random field based phone recognition , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Trevor Darrell,et al.  Hidden Conditional Random Fields , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Ben Taskar,et al.  Posterior Regularization for Structured Latent Variable Models , 2010, J. Mach. Learn. Res..

[4]  Nagarajan Natarajan,et al.  Learning with Noisy Labels , 2013, NIPS.

[5]  Guosheng Lin,et al.  Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  L. Younes.  Parametric Inference for imperfectly observed Gibbsian fields , 1989 .

[7]  Geoffrey E. Hinton,et al.  A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants , 1998, Learning in Graphical Models.

[8]  Geoffrey Zweig,et al.  From captions to visual concepts and back , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Thierry Artières,et al.  Neural conditional random fields , 2010, AISTATS.

[10]  Jian Peng,et al.  Conditional Neural Fields , 2009, NIPS.

[11]  Xiaogang Wang,et al.  Learning from massive noisy labeled data for image classification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Antonio Torralba,et al.  Semi-Supervised Learning in Gigantic Image Collections , 2009, NIPS.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[15]  Raquel Urtasun,et al.  Fully Connected Deep Structured Networks , 2015, ArXiv.

[16]  Vibhav Vineet,et al.  Conditional Random Fields as Recurrent Neural Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[17]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[18]  Martial Hebert,et al.  Learning message-passing inference machines for structured prediction , 2011, CVPR 2011.

[19]  Carsten Rother,et al.  Joint Training of Generic CNN-CRF Models with Stochastic Optimization , 2016, ACCV.

[20]  Richard Nock,et al.  Making Neural Networks Robust to Label Noise: a Loss Correction Approach , 2016, ArXiv.

[21]  Dumitru Erhan,et al.  Training Deep Neural Networks on Noisy Labels with Bootstrapping , 2014, ICLR.

[22]  Abhinav Gupta,et al.  Learning from Noisy Large-Scale Datasets with Minimal Supervision , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Ross B. Girshick,et al.  Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Vladlen Koltun,et al.  Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials , 2011, NIPS.

[25]  Geoffrey E. Hinton,et al.  Learning to Label Aerial Images from Noisy Data , 2012, ICML.

[26]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[27]  M. Verleysen,et al.  Classification in the Presence of Label Noise: A Survey , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[28]  Richard Nock,et al.  Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Alan L. Yuille,et al.  Learning Deep Structured Models , 2014, ICML.

[30]  J. Lafferty,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[31]  Joan Bruna,et al.  Training Convolutional Networks with Noisy Labels , 2014, ICLR 2014.

[32]  Bernt Schiele,et al.  What helps where – and why? Semantic relatedness for knowledge transfer , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[33]  Tijmen Tieleman,et al.  Training restricted Boltzmann machines using approximations to the likelihood gradient , 2008, ICML '08.

[34]  Xinlei Chen,et al.  Webly Supervised Learning of Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[35]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Greg Mori,et al.  Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Max Welling,et al.  Hidden-Unit Conditional Random Fields , 2011, AISTATS.