The Effectiveness of Data Augmentation in Image Classification using Deep Learning
arXiv:1712.04621
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.
8 pages, 12 figures
References in corpus (1)
Cited by in corpus (39)
- Further advantages of data augmentation on convolutional neural networks
- Improving Malaria Parasite Detection from Red Blood Cell using Deep Convolutional Neural Networks
- Deep Learning vs. Traditional Computer Vision
- Generative Image Translation for Data Augmentation in Colorectal Histopathology Images
- A Multi-cascaded Model with Data Augmentation for Enhanced Paraphrase Detection in Short Texts
- Theoretical evidence for adversarial robustness through randomization
- Augmentation Scheme for Dealing with Imbalanced Network Traffic Classification Using Deep Learning
- Technical Considerations for Semantic Segmentation in MRI using Convolutional Neural Networks
- Real-time Federated Evolutionary Neural Architecture Search
- Exploring Bias in GAN-based Data Augmentation for Small Samples
- TDEFSI: Theory Guided Deep Learning Based Epidemic Forecasting with Synthetic Information
- Using generative adversarial networks to synthesize artificial financial datasets
- Building Robust Deep Neural Networks for Road Sign Detection
- SIP-SegNet: A Deep Convolutional Encoder-Decoder Network for Joint Semantic Segmentation and Extraction of Sclera, Iris and Pupil based on Periocular Region Suppression
- Data Augmentation Using Adversarial Training for Construction-Equipment Classification
- Data Augmentation for Instrument Classification Robust to Audio Effects
- A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR
- Deep learning in bioinformatics: introduction, application, and perspective in big data era
- CIS-Net: A Novel CNN Model for Spatial Image Steganalysis via Cover Image Suppression
- Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
- Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks
- Style transfer-based image synthesis as an efficient regularization technique in deep learning
- SimEx: Express Prediction of Inter-dataset Similarity by a Fleet of Autoencoders
- Selective Synthetic Augmentation with Quality Assurance
- A Survey of Techniques All Classifiers Can Learn from Deep Networks: Models, Optimizations, and Regularization
- Automatic Data Augmentation by Learning the Deterministic Policy
- Thinking Outside the Pool: Active Training Image Creation for Relative Attributes
- Automatically Learning Data Augmentation Policies for Dialogue Tasks
- BERT for Large-scale Video Segment Classification with Test-time Augmentation
- Void region segmentation in ball grid array using u-net approach and synthetic data
- Simulation of virtual cohorts increases predictive accuracy of cognitive decline in MCI subjects
- Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation
- Improved visible to IR image transformation using synthetic data augmentation with cycle-consistent adversarial networks
- A Generative Approach Towards Improved Robotic Detection of Marine Litter
- Regularising Deep Networks with Deep Generative Models
- Implementation of Optical Deep Neural Networks using the Fabry-Perot Interferometer
- What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance
- Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation
- Handcrafted vs Deep Learning Classification for Scalable Video QoE Modeling