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 8001–8025 of 8378 papers

Title	Date	Tasks	Status	Hype
CMMC-BDRC Solution to the NLP-TEA-2018 Chinese Grammatical Error Diagnosis Task	Jul 1, 2018	Data AugmentationGeneral Classification	—Unverified	0
Semantically Equivalent Adversarial Rules for Debugging NLP models	Jul 1, 2018	Data AugmentationQuestion Answering	CodeCode Available	0
Shape-from-Mask: A Deep Learning Based Human Body Shape Reconstruction from Binary Mask Images	Jun 22, 2018	Data Augmentation	—Unverified	0
Improving brain computer interface performance by data augmentation with conditional Deep Convolutional Generative Adversarial Networks	Jun 19, 2018	Brain Computer InterfaceData Augmentation	—Unverified	0
HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules	Jun 18, 2018	Data Augmentation	CodeCode Available	0
Learning to Evaluate Image Captioning	Jun 17, 2018	8kData Augmentation	CodeCode Available	0
Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention	Jun 16, 2018	Data AugmentationDomain Adaptation	—Unverified	0
A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition	Jun 13, 2018	Data AugmentationDistant Speech Recognition	—Unverified	0
Sample Dropout for Audio Scene Classification Using Multi-Scale Dense Connected Convolutional Neural Network	Jun 12, 2018	Acoustic Scene ClassificationClassification	—Unverified	0
Data augmentation instead of explicit regularization	Jun 11, 2018	Data AugmentationObject Categorization	CodeCode Available	0
Semantically Selective Augmentation for Deep Compact Person Re-Identification	Jun 11, 2018	ClusteringData Augmentation	—Unverified	0
Transformationally Identical and Invariant Convolutional Neural Networks through Symmetric Element Operators	Jun 10, 2018	Data Augmentation	—Unverified	0
A Systematic Evaluation of Recent Deep Learning Architectures for Fine-Grained Vehicle Classification	Jun 8, 2018	ClassificationData Augmentation	CodeCode Available	0
Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data	Jun 8, 2018	Data AugmentationStochastic Optimization	—Unverified	0
Findings of the Second Workshop on Neural Machine Translation and Generation	Jun 8, 2018	Data AugmentationDomain Adaptation	—Unverified	0
Speaker-Follower Models for Vision-and-Language Navigation	Jun 7, 2018	Data AugmentationVision and Language Navigation	CodeCode Available	0
Generative Adversarial Networks for Realistic Synthesis of Hyperspectral Samples	Jun 7, 2018	Data Augmentation	—Unverified	0
Training Augmentation with Adversarial Examples for Robust Speech Recognition	Jun 7, 2018	Data AugmentationRobust Speech Recognition	—Unverified	0
EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals	Jun 5, 2018	Data AugmentationEEG	CodeCode Available	1
Study and development of a Computer-Aided Diagnosis system for classification of chest x-ray images using convolutional neural networks pre-trained for ImageNet and data augmentation	Jun 3, 2018	Data AugmentationGeneral Classification	—Unverified	0
Pose-Guided Photorealistic Face Rotation	Jun 1, 2018	Data AugmentationFace Recognition	—Unverified	0
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation	Jun 1, 2018	Data AugmentationMotion Compensation	CodeCode Available	0
DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks	Jun 1, 2018	Data AugmentationDeep Attention	—Unverified	0
Multistage Adversarial Losses for Pose-Based Human Image Synthesis	Jun 1, 2018	Data AugmentationImage Generation	—Unverified	0
Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System	Jun 1, 2018	Data AugmentationGeneral Classification	—Unverified	0

Show:10 25 50

← PrevPage 321 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