UniformAugment: A Search-free Probabilistic Data Augmentation Approach

by   Tom Ching LingChen, et al.

Augmenting training datasets has been shown to improve the learning effectiveness for several computer vision tasks. A good augmentation produces an augmented dataset that adds variability while retaining the statistical properties of the original dataset. Some techniques, such as AutoAugment and Fast AutoAugment, have introduced a search phase to find a set of suitable augmentation policies for a given model and dataset. This comes at the cost of great computational overhead, adding up to several thousand GPU hours. More recently RandAugment was proposed to substantially speedup the search phase by approximating the search space by a couple of hyperparameters, but still incurring non-negligible cost for tuning those. In this paper we show that, under the assumption that the augmentation space is approximately distribution invariant, a uniform sampling over the continuous space of augmentation transformations is sufficient to train highly effective models. Based on that result we propose UniformAugment, an automated data augmentation approach that completely avoids a search phase. In addition to discussing the theoretical underpinning supporting our approach, we also use the standard datasets, as well as established models for image classification, to show that UniformAugment's effectiveness is comparable to the aforementioned methods, while still being highly efficient by virtue of not requiring any search.


page 1

page 2

page 3

page 4


Learning Data Augmentation with Online Bilevel Optimization for Image Classification

Data augmentation is a key practice in machine learning for improving ge...

AudRandAug: Random Image Augmentations for Audio Classification

Data augmentation has proven to be effective in training neural networks...

Greedy AutoAugment

A major problem in data augmentation is the number of possibilities in t...

Fast AutoAugment

Data augmentation is an indispensable technique to improve generalizatio...

Meta Approach to Data Augmentation Optimization

Data augmentation policies drastically improve the performance of image ...

LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations

Data augmentations are important in training high-performance 3D object ...

Rotational augmentation techniques: a new perspective on ensemble learning for image classification

The popularity of data augmentation techniques in machine learning has i...

Please sign up or login with your details

Forgot password? Click here to reset