RandAugment is an automated data augmentation method. The search space for data augmentation has 2 interpretable hyperparameter $N$ and $M$. $N$ is the number of augmentation transformations to apply sequentially, and $M$ is the magnitude for all the transformations. To reduce the parameter space but still maintain image diversity, learned policies and probabilities for applying each transformation are replaced with a parameter-free procedure of always selecting a transformation with uniform probability $\frac{1}{K}$. Here $K$ is the number of transformation options. So given $N$ transformations for a training image, RandAugment may thus express $KN$ potential policies.

Transformations applied include identity transformation, autoContrast, equalize, rotation, solarixation, colorjittering, posterizing, changing contrast, changing brightness, changing sharpness, shear-x, shear-y, translate-x, translate-y.

Source: RandAugment: Practical automated data augmentation with a reduced search space

Latest Papers

PAPER DATE
Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection
Shaolei WangZhongyuan WangWanxiang CheTing Liu
2020-10-29
Self-paced Data Augmentation for Training Neural Networks
Tomoumi TakaseRyo KarakidaHideki Asoh
2020-10-29
Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
Yu ZhangJames QinDaniel S. ParkWei HanChung-Cheng ChiuRuoming PangQuoc V. LeYonghui Wu
2020-10-20
Noisy Student Training using Body Language Dataset Improves Facial Expression Recognition
Vikas KumarShivansh RaoLi Yu
2020-08-06
Semi-Supervised Learning with Data Augmentation for End-to-End ASR
Felix WeningerFranco ManaRoberto GemelloJesús Andrés-FerrerPuming Zhan
2020-07-27
SpinalNet: Deep Neural Network with Gradual Input
| H M Dipu KabirMoloud AbdarSeyed Mohammad Jafar JalaliAbbas KhosraviAmir F. AtiyaSaeid NahavandiDipti Srinivasan
2020-07-07
Training Generative Adversarial Networks with Limited Data
| Tero KarrasMiika AittalaJanne HellstenSamuli LaineJaakko LehtinenTimo Aila
2020-06-11
Improved Noisy Student Training for Automatic Speech Recognition
Daniel S. ParkYu ZhangYe JiaWei HanChung-Cheng ChiuBo LiYonghui WuQuoc V. Le
2020-05-19
On the Generalization Effects of Linear Transformations in Data Augmentation
| Sen WuHongyang R. ZhangGregory ValiantChristopher Ré
2020-05-02
UniformAugment: A Search-free Probabilistic Data Augmentation Approach
| Tom Ching LingChenAva KhonsariAmirreza LashkariMina Rafi NazariJaspreet Singh SambeeMario A. Nascimento
2020-03-31
Circumventing Outliers of AutoAugment with Knowledge Distillation
Longhui WeiAn XiaoLingxi XieXin ChenXiaopeng ZhangQi Tian
2020-03-25
Self-training with Noisy Student improves ImageNet classification
| Qizhe XieMinh-Thang LuongEduard HovyQuoc V. Le
2019-11-11
RandAugment: Practical automated data augmentation with a reduced search space
| Ekin D. CubukBarret ZophJonathon ShlensQuoc V. Le
2019-09-30

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories