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 4701–4725 of 8378 papers

Title	Date	Tasks	Status	Hype
Harnessing Hard Mixed Samples with Decoupled Regularizer	Mar 21, 2022	Data Augmentation	—Unverified	0
WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses	Mar 21, 2022	Data AugmentationDecoder	—Unverified	0
Build a Robust QA System with Transformer-based Mixture of Experts	Mar 20, 2022	Data AugmentationMixture-of-Experts	CodeCode Available	0
Partitioning Image Representation in Contrastive Learning	Mar 20, 2022	Contrastive LearningData Augmentation	—Unverified	0
A Novel Transparency Strategy-based Data Augmentation Approach for BI-RADS Classification of Mammograms	Mar 20, 2022	ClassificationData Augmentation	—Unverified	0
Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions	Mar 20, 2022	Data AugmentationSegmentation	—Unverified	0
Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model	Mar 19, 2022	Data AugmentationLanguage Modeling	CodeCode Available	0
Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition	Mar 19, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified	0
Practical Recommendations for Replay-based Continual Learning Methods	Mar 19, 2022	Continual LearningData Augmentation	—Unverified	0
Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation	Mar 18, 2022	Data AugmentationDepth Estimation	—Unverified	0
Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion	Mar 18, 2022	3D Object DetectionData Augmentation	CodeCode Available	2
SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning	Mar 18, 2022	Data AugmentationReinforcement Learning (RL)	—Unverified	0
DocXClassifier: High Performance Explainable Deep Network for Document Image Classification	Mar 17, 2022	ClassificationData Augmentation	CodeCode Available	1
Type-Driven Multi-Turn Corrections for Grammatical Error Correction	Mar 17, 2022	Data AugmentationGrammatical Error Correction	CodeCode Available	0
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation	Mar 17, 2022	Data AugmentationHellaSwag	CodeCode Available	1
MotionAug: Augmentation with Physical Correction for Human Motion Prediction	Mar 17, 2022	Data AugmentationDiversity	CodeCode Available	1
Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series	Mar 17, 2022	Contrastive LearningData Augmentation	CodeCode Available	1
Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluation	Mar 16, 2022	Data AugmentationDiversity	CodeCode Available	0
Understanding robustness and generalization of artificial neural networks through Fourier masks	Mar 16, 2022	Data Augmentation	CodeCode Available	0
Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation	Mar 16, 2022	Data AugmentationKnowledge Distillation	—Unverified	0
A Squeeze-and-Excitation and Transformer based Cross-task System for Environmental Sound Recognition	Mar 16, 2022	Acoustic Scene ClassificationData Augmentation	—Unverified	0
What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study	Mar 16, 2022	Autonomous DrivingData Augmentation	—Unverified	0
Better Quality Estimation for Low Resource Corpus Mining	Mar 15, 2022	Contrastive LearningData Augmentation	—Unverified	0
AUCO ResNet: an end-to-end network for Covid-19 pre-screening from cough and breath	Mar 15, 2022	8kAudio Classification	CodeCode Available	1
Implicit field supervision for robust non-rigid shape matching	Mar 15, 2022	Data AugmentationDecoder	CodeCode Available	1

Show:10 25 50

← PrevPage 189 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