Optimizing Data Augmentation Policy Through Random Unidimensional Search
It is no secret amongst deep learning researchers that finding the optimal data augmentation strategy during training can mean the difference between state-of-the-art performance and a run-of-the-mill result. To that end, the community has seen many efforts to automate the process of finding the perfect augmentation procedure for any task at hand. Unfortunately, even recent cutting-edge methods bring massive computational overhead, requiring as many as 100 full model trainings to settle on an ideal configuration. We show how to achieve equivalent performance using just 6 trainings with Random Unidimensional Augmentation. Source code is available at https://github.com/fastestimator/RUA/tree/v1.0
Code (1)
Tasks
Data AugmentationSimilar Papers 제목 키워드 기반
Challenges of Adversarial Image Augmentations
Image augmentations applied during training are crucial for the generalization performance of image classifiers. Therefore, a large body of research has focused on finding the optimal augmentation policy for a given task…
Randomized Policy Optimization for Optimal Stopping
Optimal stopping is the problem of determining when to stop a stochastic system in order to maximize reward, which is of practical importance in domains such as finance, operations management and healthcare. Existing met…
ManagementThe Penalty Imposed by Ablated Data Augmentation
There is a set of data augmentation techniques that ablate parts of the input at random. These include input dropout, cutout, and random erasing. We term these techniques ablated data augmentation. Though these technique…
Data AugmentationA Comprehensive Survey of Image Augmentation Techniques for Deep Learning
Deep learning has been achieving decent performance in computer vision requiring a large volume of images, however, collecting images is expensive and difficult in many scenarios. To alleviate this issue, many image augm…
Deep LearningImage AugmentationImage GenerationSurveyG-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR
Data augmentation is a ubiquitous technique used to provide robustness to automatic speech recognition (ASR) training. However, even as so much of the ASR training process has become automated and more "end-to-end", the …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentationspeech-recognition+1