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 8026–8050 of 8378 papers

Title	Date	Tasks	Status	Hype
Lyb3b at SemEval-2018 Task 11: Machine Comprehension Task using Deep Learning Models	Jun 1, 2018	Data AugmentationReading Comprehension	—Unverified	0
MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network	Jun 1, 2018	ArticlesCommon Sense Reasoning	—Unverified	0
Self-Training for Jointly Learning to Ask and Answer Questions	Jun 1, 2018	Data AugmentationQuestion Answering	—Unverified	0
Combining Pyramid Pooling and Attention Mechanism for Pelvic MR Image Semantic Segmentaion	Jun 1, 2018	Data AugmentationImage Segmentation	—Unverified	0
MONET: Multiview Semi-supervised Keypoint Detection via Epipolar Divergence	May 31, 2018	Data AugmentationKeypoint Detection	CodeCode Available	0
Accurate pedestrian localization in overhead depth images via Height-Augmented HOG	May 31, 2018	BIG-bench Machine LearningData Augmentation	—Unverified	0
Long-time predictive modeling of nonlinear dynamical systems using neural networks	May 31, 2018	Data Augmentation	—Unverified	0
Why do deep convolutional networks generalize so poorly to small image transformations?	May 30, 2018	Data AugmentationObject Recognition	CodeCode Available	1
Generalizing to Unseen Domains via Adversarial Data Augmentation	May 30, 2018	Data AugmentationSemantic Segmentation	CodeCode Available	0
Capturing Variabilities from Computed Tomography Images with Generative Adversarial Networks	May 29, 2018	Computed Tomography (CT)Data Augmentation	—Unverified	0
Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks	May 29, 2018	Brain Tumor SegmentationData Augmentation	—Unverified	0
Improved Mixed-Example Data Augmentation	May 29, 2018	Data AugmentationImage Augmentation	CodeCode Available	0
Transductive Label Augmentation for Improved Deep Network Learning	May 26, 2018	Data AugmentationGeneral Classification	—Unverified	0
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation	May 24, 2018	Data AugmentationPose Estimation	—Unverified	0
AutoAugment: Learning Augmentation Policies from Data	May 24, 2018	Data AugmentationDomain Generalization	CodeCode Available	3
Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM	May 24, 2018	Data Augmentationparameter estimation	—Unverified	0
Input and Weight Space Smoothing for Semi-supervised Learning	May 23, 2018	Data Augmentation	—Unverified	0
Enriched Long-term Recurrent Convolutional Network for Facial Micro-Expression Recognition	May 22, 2018	Data AugmentationMicro Expression Recognition	CodeCode Available	0
Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models	May 20, 2018	Data Augmentation	—Unverified	0
Abstractive Text Classification Using Sequence-to-convolution Neural Networks	May 20, 2018	ClassificationData Augmentation	CodeCode Available	0
Counterexample-Guided Data Augmentation	May 17, 2018	Autonomous DrivingData Augmentation	CodeCode Available	0
Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification	May 16, 2018	Data AugmentationPerson Re-Identification	—Unverified	0
Adversarial Training for Patient-Independent Feature Learning with IVOCT Data for Plaque Classification	May 16, 2018	Data AugmentationGeneral Classification	—Unverified	0
Resisting Large Data Variations via Introspective Transformation Network	May 16, 2018	Data AugmentationFew-Shot Learning	—Unverified	0
Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations	May 16, 2018	Data AugmentationGeneral Classification	CodeCode Available	0

Show:10 25 50

← PrevPage 322 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