VoronoiPatches: Evaluating A New Data Augmentation Method

12/20/2022
by   Steffen Illium, et al.
0

Overfitting is a problem in Convolutional Neural Networks (CNN) that causes poor generalization of models on unseen data. To remediate this problem, many new and diverse data augmentation methods (DA) have been proposed to supplement or generate more training data, and thereby increase its quality. In this work, we propose a new data augmentation algorithm: VoronoiPatches (VP). We primarily utilize non-linear recombination of information within an image, fragmenting and occluding small information patches. Unlike other DA methods, VP uses small convex polygon-shaped patches in a random layout to transport information around within an image. Sudden transitions created between patches and the original image can, optionally, be smoothed. In our experiments, VP outperformed current DA methods regarding model variance and overfitting tendencies. We demonstrate data augmentation utilizing non-linear re-combination of information within images, and non-orthogonal shapes and structures improves CNN model robustness on unseen data.

READ FULL TEXT

page 3

page 5

page 6

page 7

page 9

research
09/21/2019

Adversarial Learning of General Transformations for Data Augmentation

Data augmentation (DA) is fundamental against overfitting in large convo...
research
11/22/2018

Data Augmentation using Random Image Cropping and Patching for Deep CNNs

Deep convolutional neural networks (CNNs) have achieved remarkable resul...
research
10/17/2022

Cutting-Splicing data augmentation: A novel technology for medical image segmentation

Background: Medical images are more difficult to acquire and annotate th...
research
06/28/2021

Data augmentation for deep learning based accelerated MRI reconstruction with limited data

Deep neural networks have emerged as very successful tools for image res...
research
09/07/2023

Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection

Data augmentation (DA) is a key factor in medical image analysis, such a...
research
12/10/2022

Image augmentation with conformal mappings for a convolutional neural network

For augmentation of the square-shaped image data of a convolutional neur...
research
06/30/2020

BitMix: Data Augmentation for Image Steganalysis

Convolutional neural networks (CNN) for image steganalysis demonstrate b...

Please sign up or login with your details

Forgot password? Click here to reset