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 8176–8200 of 8378 papers

Title	Date	Tasks	Status	Hype
A Bayesian Data Augmentation Approach for Learning Deep Models	Oct 29, 2017	Data AugmentationGeneral Classification	CodeCode Available	0
A Self-Training Method for Semi-Supervised GANs	Oct 27, 2017	Data Augmentation	—Unverified	0
ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection	Oct 21, 2017	Data AugmentationObject	—Unverified	0
Convolutional Recurrent Neural Networks for Electrocardiogram Classification	Oct 17, 2017	ClassificationData Augmentation	CodeCode Available	0
DocEmul: a Toolkit to Generate Structured Historical Documents	Oct 10, 2017	Data Augmentation	CodeCode Available	0
Application of Deep Learning in Neuroradiology: Automated Detection of Basal Ganglia Hemorrhage using 2D-Convolutional Neural Networks	Oct 10, 2017	Data AugmentationGeneral Classification	—Unverified	0
Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep Chemometrics	Oct 5, 2017	Data AugmentationDeep Learning	CodeCode Available	0
Machine Learning Models that Remember Too Much	Sep 22, 2017	BIG-bench Machine LearningData Augmentation	CodeCode Available	0
ExprGAN: Facial Expression Editing with Controllable Expression Intensity	Sep 12, 2017	Data AugmentationDecoder	CodeCode Available	0
NiftyNet: a deep-learning platform for medical imaging	Sep 11, 2017	Data AugmentationDeep Learning	CodeCode Available	1
Globally Normalized Reader	Sep 8, 2017	Data AugmentationQuestion Answering	CodeCode Available	0
Learning to Compose Domain-Specific Transformations for Data Augmentation	Sep 6, 2017	Data AugmentationImage Augmentation	CodeCode Available	0
Assessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution	Sep 1, 2017	AttributeAuthorship Attribution	—Unverified	0
Incorporating Metadata into Content-Based User Embeddings	Sep 1, 2017	AttributeData Augmentation	—Unverified	0
Data Augmentation for Visual Question Answering	Sep 1, 2017	Data AugmentationGeneral Classification	—Unverified	0
Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder	Aug 30, 2017	Data AugmentationDecoder	—Unverified	0
DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation	Aug 28, 2017	3D Hand Pose EstimationData Augmentation	CodeCode Available	0
A Compromise Principle in Deep Monocular Depth Estimation	Aug 28, 2017	ClassificationData Augmentation	—Unverified	0
Deep Learning for Target Classification from SAR Imagery: Data Augmentation and Translation Invariance	Aug 26, 2017	Data AugmentationGeneral Classification	CodeCode Available	0
Learning a 3D descriptor for cross-source point cloud registration from synthetic data	Aug 24, 2017	Data AugmentationPoint Cloud Registration	—Unverified	0
Leaf Counting with Deep Convolutional and Deconvolutional Networks	Aug 24, 2017	Data AugmentationDeep Learning	CodeCode Available	0
Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations	Aug 24, 2017	3D geometry3D Geometry Prediction	CodeCode Available	0
Improving Deep Learning using Generic Data Augmentation	Aug 20, 2017	Data AugmentationDeep Learning	—Unverified	0
DeepBreath: Deep Learning of Breathing Patterns for Automatic Stress Recognition using Low-Cost Thermal Imaging in Unconstrained Settings	Aug 20, 2017	Data AugmentationMental Stress Detection	CodeCode Available	0
Applying Data Augmentation to Handwritten Arabic Numeral Recognition Using Deep Learning Neural Networks	Aug 20, 2017	Data Augmentation	—Unverified	0

Show:10 25 50

← PrevPage 328 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