The article discusses a data augmentation method based on generative adversarial networks to improve the accuracy of image classification by convolutional neural networks. A comparative analysis proposed with classical methods was performed.

Data augmentation plays a crucial role in increasing the number of training images, which often aids to improve classification performances of deep learning techniques for computer vision problems. In this paper, we employ the deep learning framework and determine the effects of several data-augmentation (DA) techniques for plant classification problems. For this, we use two convolutional neura...

Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation (Krizhevsky et al., 2012) alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given there is potential to generate a much broader set of...

This paper presents the submission of the Linguistics Department of the University of Colorado at Boulder for the 2017 CoNLL-SIGMORPHON Shared Task on Universal Morphological Reinflection. The system is implemented as an RNN Encoder-Decoder. It is specifically geared toward a low-resource setting. To this end, it employs data augmentation for counteracting overfitting and a copy symbol for proc...

The aim of livestock breeding plans is to improve an objective of selection by acting on several criteria of selection. The criteria of selection are composed by a subset of traits selected by its easiness of measure and its correlation with the objective of selection. In general, traits included on the criteria of selection are direct measures of the performance of candidates to selection. Fro...

The term data augmentation refers to methods for constructing iterative optimization or sampling algorithms via the introductionof unobserved data or latent variables. For deterministic algorithms, the method was popularized in the general statistical community by the seminal article by Dempster, Laird, and Rubin on the EM algorithm for maximizing a likelihood function or, more generally, a pos...

The rapid progress in machine learning methods has been empowered by i) huge datasets that have been collected and annotated, ii) improved engineering (e.g. data pre-processing/normalization). The existing datasets typically include several million samples, which constitutes their extension a colossal task. In addition, the state-ofthe-art data-driven methods demand a vast amount of data, hence...

This short paper considers comparisons of different data augmentation algorithms in terms of their convergence and efficiency. It examines connections between the partial order 1 on Markov kernels, and inequalities of operator norms. It applies notions from Roberts and Rosenthal (2006) related to variance bounding Markov chains, together with L2 theory, to data augmentation algorithms (Tanner a...