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
Face Attention Network: An Effective Face Detector for the Occluded Faces	Nov 20, 2017	Data AugmentationFace Detection	CodeCode Available
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks	Nov 17, 2017	Data AugmentationFace Alignment	CodeCode Available
Pseudo-positive regularization for deep person re-identification	Nov 17, 2017	Data AugmentationDiversity	—Unverified
HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images	Nov 16, 2017	Data AugmentationHand Segmentation	—Unverified
Learning Compositional Visual Concepts with Mutual Consistency	Nov 16, 2017	Data AugmentationFace Verification	—Unverified
Spectral-spatial classification of hyperspectral images: three tricks and a new supervised learning setting	Nov 15, 2017	Data AugmentationGeneral Classification	CodeCode Available
Invariances and Data Augmentation for Supervised Music Transcription	Nov 13, 2017	Data AugmentationMusic Transcription	CodeCode Available
Data Augmentation Generative Adversarial Networks	Nov 12, 2017	Data AugmentationFew-Shot Learning	CodeCode Available
Data Augmentation in Emotion Classification Using Generative Adversarial Networks	Nov 2, 2017	ClassificationData Augmentation	—Unverified
An Exploration of Data Augmentation and RNN Architectures for Question Ranking in Community Question Answering	Nov 1, 2017	BIG-bench Machine LearningCommunity Question Answering	—Unverified
Predicting Users' Negative Feedbacks in Multi-Turn Human-Computer Dialogues	Nov 1, 2017	Data Augmentation	—Unverified
Data, Depth, and Design: Learning Reliable Models for Skin Lesion Analysis	Nov 1, 2017	Data AugmentationTransfer Learning	CodeCode Available
Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels	Nov 1, 2017	Data AugmentationDecoder	—Unverified
Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction	Oct 31, 2017	Audio Source SeparationData Augmentation	CodeCode Available
A Bayesian Data Augmentation Approach for Learning Deep Models	Oct 29, 2017	Data AugmentationGeneral Classification	CodeCode Available
A Self-Training Method for Semi-Supervised GANs	Oct 27, 2017	Data Augmentation	—Unverified
ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection	Oct 21, 2017	Data AugmentationObject	—Unverified
Convolutional Recurrent Neural Networks for Electrocardiogram Classification	Oct 17, 2017	ClassificationData Augmentation	CodeCode Available
DocEmul: a Toolkit to Generate Structured Historical Documents	Oct 10, 2017	Data Augmentation	CodeCode Available
Application of Deep Learning in Neuroradiology: Automated Detection of Basal Ganglia Hemorrhage using 2D-Convolutional Neural Networks	Oct 10, 2017	Data AugmentationGeneral Classification	—Unverified
Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep Chemometrics	Oct 5, 2017	Data AugmentationDeep Learning	CodeCode Available
Machine Learning Models that Remember Too Much	Sep 22, 2017	BIG-bench Machine LearningData Augmentation	CodeCode Available
ExprGAN: Facial Expression Editing with Controllable Expression Intensity	Sep 12, 2017	Data AugmentationDecoder	CodeCode Available
Globally Normalized Reader	Sep 8, 2017	Data AugmentationQuestion Answering	CodeCode Available
Learning to Compose Domain-Specific Transformations for Data Augmentation	Sep 6, 2017	Data AugmentationImage Augmentation	CodeCode Available

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