Abstract
Image classification has become a ubiquitous task. Models trained on good quality data achieve accuracy which in some application domains is already above human-level performance. Unfortunately, real-world data are quite often degenerated by noise existing in features and/or labels. There are numerous papers that handle the problem of either feature or label noise separately. However, to the best of our knowledge, this piece of research is the first attempt to address the problem of concurrent occurrence of both types of noise. Basing on the MNIST, CIFAR-10 and CIFAR-100 datasets, we experimentally prove that the difference by which committees beat single models increases along with noise level, no matter whether it is an attribute or label disruption. Thus, it makes ensembles legitimate to be applied to noisy images with noisy labels. The aforementioned committees’ advantage over single models is positively correlated with dataset difficulty level as well. We propose three committee selection algorithms that outperform a strong baseline algorithm which relies on an ensemble of individual (nonassociated) best models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Advances in NIPS, pp. 153–160 (2007)
Breve, F.A., Zhao, L., Quiles, M.G.: Semi-supervised learning from imperfect data through particle cooperation and competition. In: The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2010)
Brodley, C.E., Friedl, M.A.: Identifying mislabeled training data. J. Artif. Intell. Res. 11, 131–167 (1999)
Brodley, C.E., Friedl, M.A., et al.: Identifying and eliminating mislabeled training instances. In: Proceedings of the National Conference on Artificial Intelligence, pp. 799–805 (1996)
Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 2, pp. 60–65. IEEE (2005)
Chan, T.H., Jia, K., Gao, S., Lu, J., Zeng, Z., Ma, Y.: PCANet: a simple deep learning baseline for image classification? IEEE Trans. Image Process. 24(12), 5017–5032 (2015)
Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3642–3649. IEEE (2012)
Croes, G.A.: A method for solving traveling-salesman problems. Oper. Res. 6(6), 791–812 (1958)
Dietterich, T.G.: An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach. Learn. 40(2), 139–157 (2000). https://doi.org/10.1023/A:1007607513941
Dodge, S., Karam, L.: A study and comparison of human and deep learning recognition performance under visual distortions. In: 2017 26th International Conference on Computer Communication and Networks (ICCCN), pp. 1–7. IEEE (2017)
Frénay, B., Verleysen, M.: Classification in the presence of label noise: a survey. IEEE Trans. Neural Netw. Learn. Syst. 25(5), 845–869 (2013)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)
González, R., Woods, R.: Digital Image Processing, vol. 60. Prentice Hall, Upper Saddle River (2008). ISBN 9780131687288
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Hickey, R.J.: Noise modelling and evaluating learning from examples. Artif. Intell. 82(1–2), 157–179 (1996)
Hughes, N.P., Roberts, S.J., Tarassenko, L.: Semi-supervised learning of probabilistic models for ECG segmentation. In: The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 1, pp. 434–437. IEEE (2004)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in NIPS, pp. 1097–1105 (2012)
Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley, Hoboken (2014)
LeCun, Y., Cortes, C., Burges, C.: MNIST handwritten digit database, 2. ATT Labs (2010). http://yann.lecun.com/exdb/mnist
Nazaré, T.S., da Costa, G.B.P., Contato, W.A., Ponti, M.: Deep convolutional neural networks and noisy images. In: Mendoza, M., Velastín, S. (eds.) CIARP 2017. LNCS, vol. 10657, pp. 416–424. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75193-1_50
Pechenizkiy, M., Tsymbal, A., Puuronen, S., Pechenizkiy, O.: Class noise and supervised learning in medical domains: the effect of feature extraction. In: 19th IEEE Symposium on Computer Based Medical Systems (CBMS 2006), pp. 708–713. IEEE (2006)
Polyak, B.T., Juditsky, A.B.: Acceleration of stochastic approximation by averaging. SIAM J. Control Optim. 30(4), 838–855 (1992)
Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986). https://doi.org/10.1007/BF00116251
Roy, S.S., Hossain, S.I., Akhand, M., Murase, K.: A robust system for noisy image classification combining denoising autoencoder and convolutional neural network. Int. J. Adv. Comput. Sci. Appl. 9(1), 224–235 (2018)
Sagi, O., Rokach, L.: Ensemble learning: a survey. Wiley Interdisc. Rev. Data Min. Knowl. Discov. 8(4), e1249 (2018)
Shapiro, L.G., Stockman, G.C.: Computer Vision. Prentice Hall, Upper Saddle River (2001)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Snow, R., O’connor, B., Jurafsky, D., Ng, A.Y.: Cheap and fast-but is it good? Evaluating non-expert annotations for natural language tasks. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp. 254–263 (2008)
Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806 (2014)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)
Zhu, X., Wu, X.: Class noise vs. attribute noise: a quantitative study. Artif. Intell. Rev. 22(3), 177–210 (2004). https://doi.org/10.1007/s10462-004-0751-8
Zhu, X., Wu, X., Chen, Q.: Bridging local and global data cleansing: identifying class noise in large, distributed data datasets. Data Min. Knowl. Disc. 12(2–3), 275–308 (2006). https://doi.org/10.1007/s10618-005-0012-8
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kaźmierczak, S., Mańdziuk, J. (2020). A Committee of Convolutional Neural Networks for Image Classification in the Concurrent Presence of Feature and Label Noise. In: Bäck, T., et al. Parallel Problem Solving from Nature – PPSN XVI. PPSN 2020. Lecture Notes in Computer Science(), vol 12269. Springer, Cham. https://doi.org/10.1007/978-3-030-58112-1_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-58112-1_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58111-4
Online ISBN: 978-3-030-58112-1
eBook Packages: Computer ScienceComputer Science (R0)