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.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 8101–8125 of 8378 papers

Title	Date	Tasks	Status	Hype
Deep Bayesian Active Semi-Supervised Learning	Mar 3, 2018	Active LearningData Augmentation	CodeCode Available	0
Improving Low Resource Machine Translation using Morphological Glosses (Non-archival Extended Abstract)	Mar 1, 2018	Data AugmentationMachine Translation	—Unverified	0
Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge	Feb 28, 2018	Brain Tumor SegmentationData Augmentation	CodeCode Available	1
Matching Convolutional Neural Networks without Priors about Data	Feb 27, 2018	Data Augmentation	CodeCode Available	0
A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector	Feb 26, 2018	Data AugmentationLicense Plate Detection	CodeCode Available	1
OhioState at SemEval-2018 Task 7: Exploiting Data Augmentation for Relation Classification in Scientific Papers using Piecewise Convolutional Neural Networks	Feb 25, 2018	ClassificationData Augmentation	—Unverified	0
Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees	Feb 24, 2018	ClassificationData Augmentation	—Unverified	0
Sensitivity and Generalization in Neural Networks: an Empirical Study	Feb 23, 2018	Data Augmentationimage-classification	—Unverified	0
Improved Techniques For Weakly-Supervised Object Localization	Feb 22, 2018	Data AugmentationObject	—Unverified	0
Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds	Feb 22, 2018	Data AugmentationTranslation	CodeCode Available	2
Conditional Adversarial Synthesis of 3D Facial Action Units	Feb 21, 2018	Data AugmentationDeep Learning	—Unverified	0
Do deep nets really need weight decay and dropout?	Feb 20, 2018	Data AugmentationObject Recognition	CodeCode Available	0
Efficient Gaussian Process Classification Using Polya-Gamma Data Augmentation	Feb 18, 2018	ClassificationData Augmentation	CodeCode Available	0
DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)	Feb 18, 2018	Data AugmentationDeep Attention	—Unverified	0
CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation	Feb 15, 2018	Data AugmentationEmotion Recognition	—Unverified	0
Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images	Feb 14, 2018	Data Augmentation	CodeCode Available	0
Predicting Adversarial Examples with High Confidence	Feb 13, 2018	Data AugmentationDiversity	—Unverified	0
Tubule segmentation of fluorescence microscopy images based on convolutional neural networks with inhomogeneity correction	Feb 10, 2018	Data AugmentationSegmentation	—Unverified	0
A Two-Stage Method for Text Line Detection in Historical Documents	Feb 9, 2018	ClusteringData Augmentation	CodeCode Available	0
Full-Frame Scene Coordinate Regression for Image-Based Localization	Feb 9, 2018	Camera RelocalizationData Augmentation	—Unverified	0
Rollable Latent Space for Azimuth Invariant SAR Target Recognition	Feb 6, 2018	Data Augmentation	—Unverified	0
Data Augmentation of Railway Images for Track Inspection	Feb 5, 2018	Data Augmentation	—Unverified	0
DxNAT - Deep Neural Networks for Explaining Non-Recurring Traffic Congestion	Jan 30, 2018	Data Augmentation	—Unverified	0
tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow	Jan 29, 2018	Data AugmentationGenerative Adversarial Network	CodeCode Available	0
Visual Data Augmentation through Learning	Jan 20, 2018	Data Augmentation	—Unverified	0

Show:10 25 50

← PrevPage 325 of 336Next →

All datasets ImageNet CIFAR-10 GA1457

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	DeiT-B (+MixPro)	Accuracy (%)	82.9	—	Unverified
2	ResNet-200 (DeepAA)	Accuracy (%)	81.32	—	Unverified
3	DeiT-S (+MixPro)	Accuracy (%)	81.3	—	Unverified
4	ResNet-200 (Fast AA)	Accuracy (%)	80.6	—	Unverified
5	ResNet-200 (UA)	Accuracy (%)	80.4	—	Unverified
6	ResNet-200 (AA)	Accuracy (%)	80	—	Unverified
7	ResNet-50 (DeepAA)	Accuracy (%)	78.3	—	Unverified
8	ResNet-50 (TA wide)	Accuracy (%)	78.07	—	Unverified
9	ResNet-50 (LoRot-E)	Accuracy (%)	77.72	—	Unverified
10	ResNet-50 (LoRot-I)	Accuracy (%)	77.71	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	WideResNet-40-2 (Faster AA)	Percentage error	3.7	—	Unverified
2	Shake-Shake (26 2×32d) (Faster AA)	Percentage error	2.7	—	Unverified
3	WideResNet-28-10 (Faster AA)	Percentage error	2.6	—	Unverified
4	Shake-Shake (26 2×112d) (Faster AA)	Percentage error	2	—	Unverified
5	Shake-Shake (26 2×96d) (Faster AA)	Percentage error	2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DiffAug	Classification Accuracy	92.7	—	Unverified
2	PaCMAP	Classification Accuracy	85.3	—	Unverified
3	hNNE	Classification Accuracy	77.4	—	Unverified
4	TopoAE	Classification Accuracy	74.6	—	Unverified