SOTAVerified

Data Augmentation

Data augmentation involves techniques used for increasing the amount of data, based on different modifications, to expand the amount of examples in the original dataset. Data augmentation not only helps to grow the dataset but it also increases the diversity of the dataset. When training machine learning models, data augmentation acts as a regularizer and helps to avoid overfitting.

Data augmentation techniques have been found useful in domains like NLP and computer vision. In computer vision, transformations like cropping, flipping, and rotation are used. In NLP, data augmentation techniques can include swapping, deletion, random insertion, among others.

Further readings:

( Image credit: Albumentations )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 7901–7950 of 8378 papers

TitleStatusHype
Transfer Incremental Learning using Data Augmentation—0
Extreme Augmentation : Can deep learning based medical image segmentation be trained using a single manually delineated scan?—0
Learning Noise-Invariant Representations for Robust Speech Recognition—0
Sheffield Submissions for WMT18 Multimodal Translation Shared Task—0
Data Augmentation for Neural Online Chats Response Selection—0
Tencent Neural Machine Translation Systems for WMT18—0
The MLLP-UPV German-English Machine Translation System for WMT18—0
T\"ubingen-Oslo system at SIGMORPHON shared task on morphological inflection. A multi-tasking multilingual sequence to sequence model.—0
Learning Text Representations for 500K Classification Tasks on Named Entity DisambiguationCode0
IPS-WASEDA system at CoNLL--SIGMORPHON 2018 Shared Task on morphological inflection—0
Deep Learning for End-to-End Atrial Fibrillation Recurrence Estimation—0
DeepSSM: A Deep Learning Framework for Statistical Shape Modeling from Raw Images—0
Hallucinations in Neural Machine Translation—0
Theoretical and Empirical Study of Adversarial Examples—0
Improving Myocardium Segmentation in Cardiac CT Angiography using Spectral Information—0
Unsupervised Adversarial Invariance—0
Flexible Mixture Modeling on Constrained Spaces—0
Adversarial Defense via Data Dependent Activation Function and Total Variation MinimizationCode0
Generative Adversarial Network in Medical Imaging: A ReviewCode2
3D Human Pose Estimation with Siamese Equivariant EmbeddingCode0
Albumentations: fast and flexible image augmentationsCode0
Déjà Vu: an empirical evaluation of the memorization properties of ConvNets—0
Style Augmentation: Data Augmentation via Style RandomizationCode0
Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose EstimationCode0
Sparse Label Smoothing Regularization for Person Re-IdentificationCode0
Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective—0
SiftingGAN: Generating and Sifting Labeled Samples to Improve the Remote Sensing Image Scene Classification Baseline in vitroCode0
Label Denoising with Large Ensembles of Heterogeneous Neural Networks—0
Capsule Deep Neural Network for Recognition of Historical Graffiti Handwriting—0
MixUp as Locally Linear Out-Of-Manifold RegularizationCode0
Learning Invariances for Policy GeneralizationCode0
Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning—0
Data Augmentation for Spoken Language Understanding via Joint Variational Generation—0
On the Importance of Visual Context for Data Augmentation in Scene Understanding—0
Data Augmentation for Skin Lesion AnalysisCode0
Aesthetic Discrimination of Graph LayoutsCode0
Data Augmentation for Neural Online Chat Response Selection—0
Generative Adversarial Network with Spatial Attention for Face Attribute EditingCode0
AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation—0
Multi-object Tracking with Neural Gating Using Bilinear LSTM—0
Open Source Dataset and Machine Learning Techniques for Automatic Recognition of Historical Graffiti—0
DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime ClassificationCode0
The Impact of Preprocessing on Deep Representations for Iris Recognition on Unconstrained Environments—0
How Robust is 3D Human Pose Estimation to Occlusion?Code0
Targeted Nonlinear Adversarial Perturbations in Images and VideosCode0
How many labeled license plates are needed?—0
Atherosclerotic carotid plaques on panoramic imaging: an automatic detection using deep learning with small dataset—0
DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN—0
SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation—0
Reducing Gender Bias in Abusive Language Detection—0
Show:102550
← PrevPage 159 of 168Next →
All datasetsImageNetCIFAR-10GA1457

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeiT-B (+MixPro)Accuracy (%)82.9—Unverified
2ResNet-200 (DeepAA)Accuracy (%)81.32—Unverified
3DeiT-S (+MixPro)Accuracy (%)81.3—Unverified
4ResNet-200 (Fast AA)Accuracy (%)80.6—Unverified
5ResNet-200 (UA)Accuracy (%)80.4—Unverified
6ResNet-200 (AA)Accuracy (%)80—Unverified
7ResNet-50 (DeepAA)Accuracy (%)78.3—Unverified
8ResNet-50 (TA wide)Accuracy (%)78.07—Unverified
9ResNet-50 (LoRot-E)Accuracy (%)77.72—Unverified
10ResNet-50 (LoRot-I)Accuracy (%)77.71—Unverified
#ModelMetricClaimedVerifiedStatus
1WideResNet-40-2 (Faster AA)Percentage error3.7—Unverified
2Shake-Shake (26 2×32d) (Faster AA)Percentage error2.7—Unverified
3WideResNet-28-10 (Faster AA)Percentage error2.6—Unverified
4Shake-Shake (26 2×112d) (Faster AA)Percentage error2—Unverified
5Shake-Shake (26 2×96d) (Faster AA)Percentage error2—Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7—Unverified
2PaCMAPClassification Accuracy85.3—Unverified
3hNNEClassification Accuracy77.4—Unverified
4TopoAEClassification Accuracy74.6—Unverified