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 8351–8378 of 8378 papers

Title	Date	Tasks	Status
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks	Apr 30, 2015	Data AugmentationModel Discovery	—Unverified
Anatomy-specific classification of medical images using deep convolutional nets	Apr 15, 2015	AnatomyClassification	—Unverified
HEp-2 Cell Image Classification with Deep Convolutional Neural Networks	Apr 10, 2015	ClassificationData Augmentation	—Unverified
Invariant backpropagation: how to train a transformation-invariant neural network	Feb 16, 2015	ClassificationData Augmentation	CodeCode Available
Multi-view Face Detection Using Deep Convolutional Neural Networks	Feb 10, 2015	Data AugmentationFace Detection	CodeCode Available
Semantic Embedding Space for Zero-Shot Action Recognition	Feb 5, 2015	Action RecognitionAttribute	—Unverified
Infinite Edge Partition Models for Overlapping Community Detection and Link Prediction	Jan 25, 2015	Community DetectionData Augmentation	—Unverified
Deep Image: Scaling up Image Recognition	Jan 13, 2015	Data AugmentationDeep Learning	—Unverified
An Analysis of Unsupervised Pre-training in Light of Recent Advances	Dec 20, 2014	Data AugmentationImage Classification	CodeCode Available
Scale-Invariant Convolutional Neural Networks	Nov 24, 2014	Data AugmentationGeneral Classification	—Unverified
"Mental Rotation" by Optimizing Transforming Distance	Jun 11, 2014	Data Augmentation	—Unverified
One Millisecond Face Alignment with an Ensemble of Regression Trees	Jun 1, 2014	Data AugmentationFace Alignment	—Unverified
Return of the Devil in the Details: Delving Deep into Convolutional Nets	May 14, 2014	Data Augmentationobject-detection	CodeCode Available
Dropout Training for Support Vector Machines	Apr 16, 2014	Data Augmentation	—Unverified
Learned versus Hand-Designed Feature Representations for 3d Agglomeration	Dec 20, 2013	Data AugmentationRetrieval	—Unverified
Unsupervised feature learning by augmenting single images	Dec 18, 2013	Data AugmentationObject Recognition	—Unverified
Scalable Inference for Logistic-Normal Topic Models	Dec 1, 2013	Data AugmentationTopic Models	—Unverified
Nonparametric Bayes dynamic modeling of relational data	Nov 19, 2013	Data AugmentationGaussian Processes	—Unverified
Disease Prediction based on Functional Connectomes using a Scalable and Spatially-Informed Support Vector Machine	Oct 21, 2013	Data AugmentationDisease Prediction	—Unverified
Gibbs Max-margin Topic Models with Data Augmentation	Oct 10, 2013	Data AugmentationGeneral Classification	—Unverified
Discriminative Relational Topic Models	Oct 9, 2013	Bayesian InferenceData Augmentation	—Unverified
Improved Bayesian Logistic Supervised Topic Models with Data Augmentation	Oct 9, 2013	Bayesian InferenceData Augmentation	—Unverified
Visual-Semantic Scene Understanding by Sharing Labels in a Context Network	Sep 16, 2013	Data AugmentationObject	—Unverified
High-Dimensional Regression with Gaussian Mixtures and Partially-Latent Response Variables	Aug 10, 2013	Data AugmentationDimensionality Reduction	—Unverified
Stochastic Pooling for Regularization of Deep Convolutional Neural Networks	Jan 16, 2013	Data AugmentationImage Classification	CodeCode Available
Augment-and-Conquer Negative Binomial Processes	Dec 1, 2012	Data Augmentation	—Unverified
Fully Bayesian inference for neural models with negative-binomial spiking	Dec 1, 2012	Bayesian InferenceData Augmentation	—Unverified
Sub-corpora Sampling with an Application to Bilingual Lexicon Extraction	Dec 1, 2012	Data Augmentation	—Unverified

Show:10 25 50

← PrevPage 168 of 168Next →

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