The Effectiveness of Data Augmentation in Image Classification using Deep Learning
read the original abstract
In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping, rotating, and flipping input images. We artificially constrain our access to data to a small subset of the ImageNet dataset, and compare each data augmentation technique in turn. One of the more successful data augmentations strategies is the traditional transformations mentioned above. We also experiment with GANs to generate images of different styles. Finally, we propose a method to allow a neural net to learn augmentations that best improve the classifier, which we call neural augmentation. We discuss the successes and shortcomings of this method on various datasets.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
Orthogonal subspace decomposition via SVD on vision foundation model features preserves high-rank pre-trained knowledge by freezing principal components and adapting residuals, reducing overfitting for better generali...
-
Modeling Spatial Extremal Dependence of Precipitation Using Distributional Neural Networks
A simulation-based generative neural network estimates parameters and nonparametric spatial dependence for max-stable processes applied to precipitation maxima.
-
Learning Data Augmentation Strategies for Object Detection
Learned data augmentation policies optimized for object detection improve COCO mAP by more than 2.3 and transfer to other datasets and models.
-
Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments
Machine learning methods including denoising autoencoders, unsupervised interference mitigation, blind source separation, and certifiable classification are developed and experimentally validated to improve multi-spec...
-
A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence
A conditional Wasserstein GAN generates plausible future SWI drought trajectories for French insurance risk management under climate change.
-
Further advantages of data augmentation on convolutional neural networks
Data augmentation enables CNNs to adapt to varying architectures and data amounts without hyperparameter fine-tuning, unlike weight decay and dropout.
-
Data Augmentation for Instrument Classification Robust to Audio Effects
Data augmentation with audio effects is evaluated as a way to make instrument classification models robust to processing commonly used in electronic music production.
-
Improving Malaria Parasite Detection from Red Blood Cell using Deep Convolutional Neural Networks
CNNs applied to the NIH malaria dataset reach 97.77% accuracy for parasite detection in segmented RBC patches using 5-fold cross-validation and holdout testing.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.