Fetching the paper…

Reading the bibliography…

2016

Understanding data augmentation for classification: when to warp?

Wong, Sebastien C., Gatt, Adam, Stamatescu, Victor et al.

Original
PDF
Post on X

Understand

In this paper we investigate the benefit of augmenting data with synthetically created samples when training a machine learning classifier.

Two approaches for creating additional training samples are data warping, which generates additional samples through transformations applied in the data-space, and synthetic over-sampling, which creates additional samples in feature-space.
We experimentally evaluate the benefits of data augmentation for a convolutional backpropagation-trained neural network, a convolutional support vector machine and a convolutional extreme learning machine classifier, using the standard MNIST handwritten digit dataset.
We found that while it is possible to perform generic augmentation in feature-space, if plausible transforms for the data are known then augmentation in data-space provides a greater benefit for improving performance and reducing overfitting.

Understanding data augmentation for classification: when to warp? · Around

Built on

H. S. Baird, “Document image defect models,” in Structured Document Image Analysis . Springer, 1992, pp. 546–556
1992
Earlier work this paper cites.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE , vol. 86, no. 11, pp. 2278–2324, 1998
1998
Earlier work this paper cites.
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “Smote: synthetic minority over-sampling technique,” Journal of artificial intelligence research , vol. 16, no. 1, pp. 321–357, 2002
2002
Earlier work this paper cites.
P. Y. Simard, D. Steinkraus, and J. C. Platt, “Best practices for convolutional neural networks applied to visual document analysis,” in 2013 12th International Conference on Document Analysis and Recognition , vol. 2. IEEE Computer Society, 2003, pp. 958–958
2003
Earlier work this paper cites.
D. C. Ciresan, U. Meier, L. M. Gambardella, and J. Schmidhuber, “Deep, big, simple neural nets for handwritten digit recognition,” Neural computation , vol. 22, no. 12, pp. 3207–3220, 2010
2010
Earlier work this paper cites.
A. Coates, A. Y. Ng, and H. Lee, “An analysis of single-layer networks in unsupervised feature learning,” in International conference on artificial intelligence and statistics , 2011, pp. 215–223
2011
Earlier work this paper cites.

Similar

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in neural information processing systems , 2012, pp. 1097–1105
2012
Cited alongside, same era.
C. Bunkhumpornpat, K. Sinapiromsaran, and C. Lursinsap, “Dbsmote: density-based synthetic minority over-sampling technique,” Applied Intelligence , vol. 36, no. 3, pp. 664–684, 2012
2012
Cited alongside, same era.
P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun, “Overfeat: Integrated recognition, localization and detection using convolutional networks,” arXiv preprint arXiv:1312.6229 , 2013
Original
2013
Cited alongside, same era.
A. G. Howard, “Some improvements on deep convolutional neural network based image classification,” arXiv preprint arXiv:1312.5402 , 2013
Original
2013
Cited alongside, same era.

Then

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2015, pp. 1–9
2015
Later among the works it cites.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” arXiv preprint arXiv:1512.03385 , 2015
Original
2015
Later among the works it cites.
M. D. McDonnell and T. Vladusich, “Enhanced image classification with a fast-learning shallow convolutional neural network,” arXiv preprint arXiv:1503.04596 , 2015
Original
2015
Later among the works it cites.
X. Zhang, Y. Fu, A. Zang, L. Sigal, and G. Agam, “Learning classifiers from synthetic data using a multichannel autoencoder,” arXiv preprint arXiv:1503.03163 , 2015
Original
2015
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556 , 2014

2014

Cited alongside, same era.

L. Yaeger, R. Lyon, and B. Webb, “Effective training of a neural network character classifier for word recognition.”

Cited in the paper.

I. Sato, H. Nishimura, and K. Yokoi, “Apac: Augmented pattern classification with neural networks,” arXiv preprint arXiv:1505.03229 , 2015

2015

Later among the works it cites.