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 7626–7650 of 8378 papers

Title	Date	Tasks	Status
Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition	Jul 17, 2019	Autonomous DrivingData Augmentation	—Unverified
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming	Jul 17, 2019	Autonomous DrivingBenchmarking	CodeCode Available
Neural Language Model Based Training Data Augmentation for Weakly Supervised Early Rumor Detection	Jul 16, 2019	Data AugmentationLanguage Modeling	CodeCode Available
Human Pose Estimation for Real-World Crowded Scenarios	Jul 16, 2019	Data AugmentationObject Recognition	CodeCode Available
Deep Sequential Mosaicking of Fetoscopic Videos	Jul 15, 2019	Data Augmentation	CodeCode Available
Multi-hop Federated Private Data Augmentation with Sample Compression	Jul 15, 2019	Data Augmentation	—Unverified
Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling	Jul 15, 2019	Acoustic Scene ClassificationData Augmentation	—Unverified
Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation	Jul 14, 2019	Data AugmentationMachine Translation	—Unverified
FMRI data augmentation via synthesis	Jul 13, 2019	Data AugmentationGenerative Adversarial Network	—Unverified
A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data	Jul 8, 2019	3D Action RecognitionAction Recognition	—Unverified
Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent	Jul 8, 2019	Data AugmentationDecoder	CodeCode Available
Affine Disentangled GAN for Interpretable and Robust AV Perception	Jul 6, 2019	Adversarial AttackAutonomous Vehicles	—Unverified
The DKU Replay Detection System for the ASVspoof 2019 Challenge: On Data Augmentation, Feature Representation, Classification, and Fusion	Jul 5, 2019	Data AugmentationGeneral Classification	—Unverified
End-to-End Speech Recognition with High-Frame-Rate Features Extraction	Jul 3, 2019	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified
Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applications	Jul 2, 2019	Data AugmentationEdge-computing	CodeCode Available
Improving the Robustness of Question Answering Systems to Question Paraphrasing	Jul 1, 2019	Data AugmentationQuestion Answering	CodeCode Available
On the Summarization of Consumer Health Questions	Jul 1, 2019	Data AugmentationQuestion Answering	CodeCode Available
Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation	Jul 1, 2019	Data AugmentationMachine Translation	—Unverified
The University of Sydney's Machine Translation System for WMT19	Jun 30, 2019	Data AugmentationMachine Translation	—Unverified
Effective Rotation-invariant Point CNN with Spherical Harmonics kernels	Jun 27, 2019	Data Augmentation	CodeCode Available
Further advantages of data augmentation on convolutional neural networks	Jun 26, 2019	Data Augmentation	—Unverified
Mixup of Feature Maps in a Hidden Layer for Training of Convolutional Neural Network	Jun 24, 2019	Data Augmentationimage-classification	—Unverified
Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting	Jun 23, 2019	Data Augmentation	CodeCode Available
Detection of Myocardial Infarction Based on Novel Deep Transfer Learning Methods for Urban Healthcare in Smart Cities	Jun 22, 2019	Data AugmentationDiagnostic	—Unverified
A Fourier Perspective on Model Robustness in Computer Vision	Jun 21, 2019	Data Augmentation	—Unverified

Show:10 25 50

← PrevPage 306 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