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 6101–6125 of 8378 papers

Title	Date	Tasks	Status	Hype
Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN	Mar 8, 2021	Adversarial DefenseAdversarial Robustness	—Unverified	0
What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels	Mar 7, 2021	Data AugmentationScene Text Recognition	CodeCode Available	1
Modeling tail risks of inflation using unobserved component quantile regressions	Mar 5, 2021	Bayesian InferenceData Augmentation	CodeCode Available	1
VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges	Mar 5, 2021	Action RecognitionData Augmentation	CodeCode Available	1
FloMo: Tractable Motion Prediction with Normalizing Flows	Mar 5, 2021	Data AugmentationDensity Estimation	CodeCode Available	0
Neural model robustness for skill routing in large-scale conversational AI systems: A design choice exploration	Mar 4, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified	0
Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision	Mar 4, 2021	Data AugmentationPose Transfer	—Unverified	0
Automated Detection of Coronary Artery Stenosis in X-ray Angiography using Deep Neural Networks	Mar 4, 2021	BlockingData Augmentation	—Unverified	0
Data Augmentation for Object Detection via Differentiable Neural Rendering	Mar 4, 2021	Data AugmentationNeural Rendering	CodeCode Available	1
Domain Generalization: A Survey	Mar 3, 2021	Action RecognitionData Augmentation	—Unverified	0
Multi-attentional Deepfake Detection	Mar 3, 2021	Binary ClassificationData Augmentation	CodeCode Available	1
Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing	Mar 3, 2021	Data AugmentationQuestion Generation	—Unverified	0
On the effectiveness of adversarial training against common corruptions	Mar 3, 2021	Data Augmentation	CodeCode Available	1
Bulk Production Augmentation Towards Explainable Melanoma Diagnosis	Mar 3, 2021	Data AugmentationDiagnostic	—Unverified	0
Pseudo-labeling for Scalable 3D Object Detection	Mar 2, 2021	3D Object DetectionAutonomous Vehicles	—Unverified	0
ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations	Mar 2, 2021	Atomic ForcesComputational Efficiency	—Unverified	0
Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoML	Mar 2, 2021	AutoMLBIG-bench Machine Learning	CodeCode Available	0
Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning	Mar 2, 2021	BIG-bench Machine LearningContrastive Learning	CodeCode Available	0
Diffusion Probabilistic Models for 3D Point Cloud Generation	Mar 2, 2021	Data AugmentationPoint Cloud Generation	CodeCode Available	1
Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation	Mar 2, 2021	Data AugmentationObject	CodeCode Available	1
Data Augmentation for Abstractive Query-Focused Multi-Document Summarization	Mar 2, 2021	Data AugmentationDocument Summarization	CodeCode Available	1
Fixing Data Augmentation to Improve Adversarial Robustness	Mar 2, 2021	Adversarial RobustnessData Augmentation	CodeCode Available	1
SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification	Mar 2, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Accounting for Variance in Machine Learning Benchmarks	Mar 1, 2021	BenchmarkingBIG-bench Machine Learning	—Unverified	0
DTW-Merge: A Novel Data Augmentation Technique for Time Series Classification	Mar 1, 2021	Data AugmentationDynamic Time Warping	CodeCode Available	0

Show:10 25 50

← PrevPage 245 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