Improving Deep Learning using Generic Data Augmentation

By Luke Taylor, Geoff Stuart Nitschke. arXiv.org, 2017

396 citations recorded by the source corpus.

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 augmentation overcomes this issue by artificially inflating the training set with label preserving transformations. Recently there has been extensive use of generic data augmentation to improve Convolutional Neural Network (CNN) task performance. This study benchmarks various popular data augmentation schemes to allow researchers to make informed decisions as to which training methods are most appropriate for their data sets. Various geometric and photometric schemes are evaluated on a coarse-grained data set using a relatively simple CNN. Experimental results, run using 4-fold cross-validation and reported in terms of Top-1 and Top-5 accuracy, indicate that cropping in geometric augmentation significantly increases CNN task performance.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6bb558052ba9f3288983e6ace964cf9ce52c1afd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Label-Only Membership Inference Attacks (2020, background): “Data augmentation is commonly used in machine learning to prevent a model from overfitting, in particular in low data regimes [29, 54, 55, 56, 57].”
A survey on Image Data Augmentation for Deep Learning (2019, methodology): “They tested these augmentations with 4-fold cross-validation on the Caltech101 dataset filtered to 8421 images of size 256 × 256 (Table 1).”
An Empirical Survey of Data Augmentation for Limited Data Learning in NLP (2021, methodology): “Such techniques have been widely explored in the computer vision field, with methods like geometric/color space transformations (Simard et al., 2003; Krizhevsky et al., 2012; Taylor and Nitschke, 2017), mixup (Zhang et al.”
Computer-Aided Diagnosis in the Era of Deep Learning (2020, background): “Data augmentation has been shown to reduce the risk of overfitting to a small training set and improve generalizability by introducing some variations or jittering to the original data 31,51,52 .”
Neurosymbolic Programming (2021, background): “A final category in this topic is programmatic supervision (Ratner et al., 2016; Zhan et al., 2020), which is closely related to the concepts of self-supervision (Hendrycks et al., 2019; Chen et al., 2020a) and data augmentation (Taylor and Nitschke, 2017).”
Improved YOLOv5 network for real-time multi-scale traffic sign detection (2021, methodology): “2 Data augmentation Data augmentation has been widely utilized for network optimization and proven to be beneficial in vision tasks[2, 8, 27], which can improve the performance of CNN, prevent over-fitting [28], and is easy to implement [29].”
A survey on face data augmentation for the training of deep neural networks (2019, methodology): “Taylor et al. [130] demonstrated the effectiveness of using basic geometric and photometric data augmentation schemes like cropping, rotation, etc., to help researchers ﬁnd the most appropriate choice for their dataset.”