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 7651–7675 of 8378 papers

Title	Date	Tasks	Status
Adversarial Self-Paced Learning for Mixture Models of Hawkes Processes	Jun 20, 2019	Data Augmentation	—Unverified
Data Interpolating Prediction: Alternative Interpretation of Mixup	Jun 20, 2019	Data AugmentationGeneral Classification	—Unverified
Efficient data augmentation using graph imputation neural networks	Jun 20, 2019	Data AugmentationImputation	—Unverified
Predicting Confusion from Eye-Tracking Data with Recurrent Neural Networks	Jun 19, 2019	Data AugmentationSensitivity	CodeCode Available
Generalizing Back-Translation in Neural Machine Translation	Jun 17, 2019	Data AugmentationMachine Translation	—Unverified
Can neural networks understand monotonicity reasoning?	Jun 15, 2019	Data AugmentationNatural Language Inference	CodeCode Available
Learning to Ask Unanswerable Questions for Machine Reading Comprehension	Jun 14, 2019	Data AugmentationMachine Reading Comprehension	—Unverified
CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training Budgets	Jun 13, 2019	Data Augmentation	CodeCode Available
Mask2Lesion: Mask-Constrained Adversarial Skin Lesion Image Synthesis	Jun 13, 2019	Data AugmentationImage Generation	—Unverified
Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise	Jun 13, 2019	Data AugmentationDecoder	—Unverified
A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR	Jun 13, 2019	Data Augmentation	—Unverified
Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection	Jun 12, 2019	3D Object DetectionData Augmentation	—Unverified
Warping Resilient Scalable Anomaly Detection in Time Series	Jun 12, 2019	Anomaly DetectionComputational Efficiency	—Unverified
Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation	Jun 11, 2019	Data AugmentationDecoder	—Unverified
Learning robust visual representations using data augmentation invariance	Jun 11, 2019	Data AugmentationObject Categorization	CodeCode Available
iProStruct2D: Identifying protein structural classes by deep learning via 2D representations	Jun 11, 2019	Data AugmentationGeneral Classification	—Unverified
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology	Jun 11, 2019	counterfactualData Augmentation	—Unverified
Automatic brain tissue segmentation in fetal MRI using convolutional neural networks	Jun 11, 2019	Data AugmentationSegmentation	—Unverified
Generalized Data Augmentation for Low-Resource Translation	Jun 10, 2019	Data AugmentationMachine Translation	—Unverified
An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance	Jun 10, 2019	ClusteringData Augmentation	CodeCode Available
A Preliminary Study on Data Augmentation of Deep Learning for Image Classification	Jun 9, 2019	Data AugmentationDeep Learning	—Unverified
When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation	Jun 7, 2019	Data AugmentationDomain Adaptation	CodeCode Available
Bad Global Minima Exist and SGD Can Reach Them	Jun 6, 2019	Data Augmentationimage-classification	CodeCode Available
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation	Jun 6, 2019	Data Augmentationobject-detection	CodeCode Available
Practical Deep Learning with Bayesian Principles	Jun 6, 2019	Continual LearningData Augmentation	CodeCode Available

Show:10 25 50

← PrevPage 307 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