A survey on data‐efficient algorithms in big data era

A Adadi - Journal of Big Data, 2021 - Springer
The leading approaches in Machine Learning are notoriously data-hungry. Unfortunately,
many application domains do not have access to big data because acquiring data involves a …

Understanding data augmentation for classification: when to warp?

SC Wong, A Gatt, V Stamatescu… - … conference on digital …, 2016 - ieeexplore.ieee.org
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 …

Improving deep learning with generic data augmentation

L Taylor, G Nitschke - 2018 IEEE symposium series on …, 2018 - ieeexplore.ieee.org
Deep artificial neural networks require a large corpus of training data in order to effectively
learn, where collection of such training data is often expensive and laborious. Data …

Understanding and mitigating the tradeoff between robustness and accuracy

A Raghunathan, SM Xie, F Yang, J Duchi… - arXiv preprint arXiv …, 2020 - arxiv.org
Adversarial training augments the training set with perturbations to improve the robust error
(over worst-case perturbations), but it often leads to an increase in the standard error (on …

Supervised autoencoders: Improving generalization performance with unsupervised regularizers

L Le, A Patterson, M White - Advances in neural information …, 2018 - proceedings.neurips.cc
Generalization performance is a central goal in machine learning, particularly when learning
representations with large neural networks. A common strategy to improve generalization …

Improving deep learning using generic data augmentation

L Taylor, G Nitschke - arXiv preprint arXiv:1708.06020, 2017 - arxiv.org
Deep artificial neural networks require a large corpus of training data in order to effectively
learn, where collection of such training data is often expensive and laborious. Data …

A bayesian data augmentation approach for learning deep models

T Tran, T Pham, G Carneiro… - Advances in neural …, 2017 - proceedings.neurips.cc
Data augmentation is an essential part of the training process applied to deep learning
models. The motivation is that a robust training process for deep learning models depends …

[PDF][PDF] Style augmentation: data augmentation via style randomization.

PTG Jackson, AA Abarghouei, S Bonner… - CVPR …, 2019 - openaccess.thecvf.com
We introduce style augmentation, a new form of data augmentation based on random style
transfer, for improving the robustness of Convolutional Neural Networks (CNN) over both …

[PDF][PDF] Best practices for convolutional neural networks applied to visual document analysis.

PY Simard, D Steinkraus, JC Platt - Icdar, 2003 - researchgate.net
Neural networks are a powerful technology for classification of visual inputs arising from
documents. However, there is a confusing plethora of different neural network methods that …

Data augmentation as feature manipulation

R Shen, S Bubeck… - … conference on machine …, 2022 - proceedings.mlr.press
Data augmentation is a cornerstone of the machine learning pipeline, yet its theoretical
underpinnings remain unclear. Is it merely a way to artificially augment the data set size? Or …