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 8101–8150 of 8378 papers

TitleStatusHype
Deep Bayesian Active Semi-Supervised LearningCode0
Improving Low Resource Machine Translation using Morphological Glosses (Non-archival Extended Abstract)—0
Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 ChallengeCode1
Matching Convolutional Neural Networks without Priors about DataCode0
A Robust Real-Time Automatic License Plate Recognition Based on the YOLO DetectorCode1
OhioState at SemEval-2018 Task 7: Exploiting Data Augmentation for Relation Classification in Scientific Papers using Piecewise Convolutional Neural Networks—0
Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees—0
Sensitivity and Generalization in Neural Networks: an Empirical Study—0
Improved Techniques For Weakly-Supervised Object Localization—0
Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudsCode2
Conditional Adversarial Synthesis of 3D Facial Action Units—0
Do deep nets really need weight decay and dropout?Code0
Efficient Gaussian Process Classification Using Polya-Gamma Data AugmentationCode0
DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)—0
CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation—0
Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR ImagesCode0
Predicting Adversarial Examples with High Confidence—0
Tubule segmentation of fluorescence microscopy images based on convolutional neural networks with inhomogeneity correction—0
A Two-Stage Method for Text Line Detection in Historical DocumentsCode0
Full-Frame Scene Coordinate Regression for Image-Based Localization—0
Rollable Latent Space for Azimuth Invariant SAR Target Recognition—0
Data Augmentation of Railway Images for Track Inspection—0
DxNAT - Deep Neural Networks for Explaining Non-Recurring Traffic Congestion—0
tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid FlowCode0
Visual Data Augmentation through Learning—0
3D CNN-based classification using sMRI and MD-DTI images for Alzheimer disease studies—0
Feature Space Transfer for Data Augmentation—0
Inferring a Third Spatial Dimension from 2D Histological Images—0
Data Augmentation for Brain-Computer Interfaces: Analysis on Event-Related Potentials Data—0
SketchyGAN: Towards Diverse and Realistic Sketch to Image SynthesisCode0
Data Augmentation by Pairing Samples for Images Classification—0
Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification—0
Anatomical Data Augmentation For CNN based Pixel-wise Classification—0
Building Generalizable Agents with a Realistic and Rich 3D EnvironmentCode0
Enhanced Image Classification With Data Augmentation Using Position Coordinates—0
DENSER: Deep Evolutionary Network Structured RepresentationCode0
Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM—0
On the Generalization Effects of DenseNet Model Structures—0
Transfer Learning on Manifolds via Learned Transport Operators—0
Evaluation of generative networks through their data augmentation capacity—0
Grouping-By-ID: Guarding Against Adversarial Domain Shifts—0
VOCABULARY-INFORMED VISUAL FEATURE AUGMENTATION FOR ONE-SHOT LEARNING—0
Neural Collaborative Autoencoder—0
Enhance Visual Recognition under Adverse Conditions via Deep Networks—0
Improved Regularization Techniques for End-to-End Speech Recognition—0
The Effectiveness of Data Augmentation in Image Classification using Deep LearningCode0
The Effectiveness of Data Augmentation for Detection of Gastrointestinal Diseases from Endoscopical Images—0
Capsule Network Performance on Complex Data—0
Quantifying Translation-Invariance in Convolutional Neural Networks—0
Music Transcription by Deep Learning with Data and "Artificial Semantic" Augmentation—0
Show:102550
← PrevPage 163 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