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 8251–8275 of 8378 papers

Title	Date	Tasks	Status	Hype
Inference of epidemiological parameters from household stratified data	Mar 21, 2017	Bayesian InferenceComputational Efficiency	—Unverified	0
SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules	Mar 21, 2017	Data Augmentation	CodeCode Available	0
I2T2I: Learning Text to Image Synthesis with Textual Data Augmentation	Mar 20, 2017	Caption GenerationData Augmentation	—Unverified	0
Multilevel Context Representation for Improving Object Recognition	Mar 19, 2017	Data AugmentationObject	—Unverified	0
Global and Local Information Based Deep Network for Skin Lesion Segmentation	Mar 16, 2017	Data AugmentationLesion Segmentation	—Unverified	0
A Localisation-Segmentation Approach for Multi-label Annotation of Lumbar Vertebrae using Deep Nets	Mar 13, 2017	Data Augmentation	—Unverified	0
Prostate Cancer Diagnosis using Deep Learning with 3D Multiparametric MRI	Mar 12, 2017	BIG-bench Machine LearningData Augmentation	—Unverified	0
Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis	Mar 10, 2017	Color ConstancyColor Normalization	—Unverified	0
TumorNet: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Process	Mar 2, 2017	Data AugmentationLung Cancer Diagnosis	—Unverified	0
Learning Discrete Representations via Information Maximizing Self-Augmented Training	Feb 28, 2017	ClusteringData Augmentation	CodeCode Available	0
Convolutional Neural Network Committees for Melanoma Classification with Classical And Expert Knowledge Based Image Transforms Data Augmentation	Feb 22, 2017	Data AugmentationGeneral Classification	—Unverified	0
Effective face landmark localization via single deep network	Feb 9, 2017	Data AugmentationFace Alignment	—Unverified	0
Video Salient Object Detection via Fully Convolutional Networks	Feb 2, 2017	Data AugmentationObject	—Unverified	0
Pooling Facial Segments to Face: The Shallow and Deep Ends	Jan 29, 2017	Data AugmentationFace Detection	—Unverified	0
Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification	Jan 23, 2017	ClassificationData Augmentation	CodeCode Available	0
Bayesian Non-Homogeneous Markov Models via Polya-Gamma Data Augmentation with Applications to Rainfall Modeling	Jan 11, 2017	Data Augmentationspeech-recognition	—Unverified	0
Deep Learning for Logo Recognition	Jan 10, 2017	Data AugmentationDeep Learning	—Unverified	0
AENet: Learning Deep Audio Features for Video Analysis	Jan 3, 2017	Action RecognitionData Augmentation	CodeCode Available	0
Harmonic Networks: Deep Translation and Rotation Equivariance	Dec 14, 2016	Data AugmentationRotated MNIST	CodeCode Available	1
AGA: Attribute Guided Augmentation	Dec 8, 2016	AttributeData Augmentation	CodeCode Available	0
Food Image Recognition by Using Convolutional Neural Networks (CNNs)	Dec 3, 2016	Data AugmentationGeneral Classification	CodeCode Available	0
Breast Mass Classification from Mammograms using Deep Convolutional Neural Networks	Dec 2, 2016	ClassificationData Augmentation	CodeCode Available	0
Japanese Text Normalization with Encoder-Decoder Model	Dec 1, 2016	Data AugmentationDecoder	—Unverified	0
Towards Robust Deep Neural Networks with BANG	Dec 1, 2016	BIG-bench Machine LearningData Augmentation	—Unverified	0
Hyperspectral CNN Classification with Limited Training Samples	Nov 28, 2016	ClassificationData Augmentation	—Unverified	0

Show:10 25 50

← PrevPage 331 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 2×96d) (Faster AA)	Percentage error	2	—	Unverified
5	Shake-Shake (26 2×112d) (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