A Bayesian Data Augmentation Approach for Learning Deep Models

10/29/2017
by   Toan Tran, et al.
0

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 on large annotated datasets, which are expensive to be acquired, stored and processed. Therefore a reasonable alternative is to be able to automatically generate new annotated training samples using a process known as data augmentation. The dominant data augmentation approach in the field assumes that new training samples can be obtained via random geometric or appearance transformations applied to annotated training samples, but this is a strong assumption because it is unclear if this is a reliable generative model for producing new training samples. In this paper, we provide a novel Bayesian formulation to data augmentation, where new annotated training points are treated as missing variables and generated based on the distribution learned from the training set. For learning, we introduce a theoretically sound algorithm --- generalised Monte Carlo expectation maximisation, and demonstrate one possible implementation via an extension of the Generative Adversarial Network (GAN). Classification results on MNIST, CIFAR-10 and CIFAR-100 show the better performance of our proposed method compared to the current dominant data augmentation approach mentioned above --- the results also show that our approach produces better classification results than similar GAN models.

READ FULL TEXT
research
04/26/2019

Bayesian Generative Active Deep Learning

Deep learning models have demonstrated outstanding performance in severa...
research
10/18/2019

Automatic Data Augmentation by Learning the Deterministic Policy

Aiming to produce sufficient and diverse training samples, data augmenta...
research
05/29/2018

Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks

There is a common belief that the successful training of deep neural net...
research
10/24/2019

Superposition as Data Augmentation using LSTM and HMM in Small Training Sets

Considering audio and image data as having quantum nature (data are repr...
research
01/25/2021

Few-Shot Website Fingerprinting Attack

This work introduces a novel data augmentation method for few-shot websi...
research
09/28/2016

Understanding data augmentation for classification: when to warp?

In this paper we investigate the benefit of augmenting data with synthet...
research
12/09/2020

Generative Adversarial Networks for Annotated Data Augmentation in Data Sparse NLU

Data sparsity is one of the key challenges associated with model develop...

Please sign up or login with your details

Forgot password? Click here to reset