ParticleAugment: Sampling-Based Data Augmentation

06/16/2021
by   Alexander Tsaregorodtsev, et al.
7

We present an automated data augmentation approach for image classification. We formulate the problem as Monte Carlo sampling where our goal is to approximate the optimal augmentation policies. We propose a particle filtering formulation to find optimal augmentation policies and their schedules during model training. Our performance measurement procedure relies on a validation subset of our training set, while the policy transition model depends on a Gaussian prior and an optional augmentation velocity parameter. In our experiments, we show that our formulation for automated augmentation reaches promising results on CIFAR-10, CIFAR-100, and ImageNet datasets using the standard network architectures for this problem. By comparing with the related work, we also show that our method reaches a balance between the computational cost of policy search and the model performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/24/2019

Adversarial AutoAugment

Data augmentation (DA) has been widely utilized to improve generalizatio...
research
05/04/2023

LatentAugment: Dynamically Optimized Latent Probabilities of Data Augmentation

Although data augmentation is a powerful technique for improving the per...
research
12/22/2020

MetaAugment: Sample-Aware Data Augmentation Policy Learning

Automated data augmentation has shown superior performance in image reco...
research
04/20/2023

LA3: Efficient Label-Aware AutoAugment

Automated augmentation is an emerging and effective technique to search ...
research
05/06/2019

Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks

In recent years, deep learning has achieved remarkable achievements in m...
research
10/18/2019

Automatic Data Augmentation by Learning the Deterministic Policy

Aiming to produce sufficient and diverse training samples, data augmenta...
research
06/07/2021

MixRL: Data Mixing Augmentation for Regression using Reinforcement Learning

Data augmentation is becoming essential for improving regression accurac...

Please sign up or login with your details

Forgot password? Click here to reset