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 3901–3925 of 8378 papers

Title	Date	Tasks	Status	Hype
Evaluating the Performance of StyleGAN2-ADA on Medical Images	Oct 7, 2022	Computed Tomography (CT)Data Augmentation	—Unverified	0
In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?	Oct 7, 2022	Data AugmentationDeep Learning	—Unverified	0
UU-Tax at SemEval-2022 Task 3: Improving the generalizability of language models for taxonomy classification through data augmentation	Oct 7, 2022	Binary ClassificationData Augmentation	CodeCode Available	0
Trustworthiness of Laser-Induced Breakdown Spectroscopy Predictions via Simulation-based Synthetic Data Augmentation and Multitask Learning	Oct 7, 2022	Data AugmentationDimensionality Reduction	—Unverified	0
Automated segmentation and morphological characterization of placental histology images based on a single labeled image	Oct 7, 2022	Data AugmentationDiversity	CodeCode Available	1
On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processing	Oct 6, 2022	Code ClassificationData Augmentation	CodeCode Available	0
A ResNet is All You Need? Modeling A Strong Baseline for Detecting Referable Diabetic Retinopathy in Fundus Images	Oct 6, 2022	AllData Augmentation	CodeCode Available	0
BootAug: Boosting Text Augmentation via Hybrid Instance Filtering Framework	Oct 6, 2022	ClassificationData Augmentation	CodeCode Available	1
MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentation	Oct 6, 2022	ClassificationCode Classification	CodeCode Available	1
Data-driven Approaches to Surrogate Machine Learning Model Development	Oct 6, 2022	Data AugmentationTransfer Learning	—Unverified	0
Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding	Oct 6, 2022	3D Object ClassificationContrastive Learning	CodeCode Available	1
GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks	Oct 5, 2022	Data AugmentationGenerative Adversarial Network	—Unverified	0
Transformer-based conditional generative adversarial network for multivariate time series generation	Oct 5, 2022	Data AugmentationGenerative Adversarial Network	CodeCode Available	1
The Vendi Score: A Diversity Evaluation Metric for Machine Learning	Oct 5, 2022	Data AugmentationDiversity	CodeCode Available	1
TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene	Oct 5, 2022	AutoMLData Augmentation	—Unverified	0
The Calibration Generalization Gap	Oct 5, 2022	Data Augmentation	CodeCode Available	1
Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift	Oct 4, 2022	Data AugmentationImage Segmentation	—Unverified	0
Code-Switching without Switching: Language Agnostic End-to-End Speech Translation	Oct 4, 2022	Data Augmentationspeech-recognition	—Unverified	0
PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes	Oct 4, 2022	Autonomous DrivingData Augmentation	CodeCode Available	1
Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation	Oct 4, 2022	Data AugmentationNatural Language Inference	—Unverified	0
rPPG-Toolbox: Deep Remote PPG Toolbox	Oct 3, 2022	BenchmarkingData Augmentation	CodeCode Available	2
MultiLoad-GAN: A GAN-Based Synthetic Load Group Generation Method Considering Spatial-Temporal Correlations	Oct 3, 2022	Data AugmentationGenerative Adversarial Network	—Unverified	0
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems	Oct 3, 2022	Binary ClassificationData Augmentation	—Unverified	0
Smooth image-to-image translations with latent space interpolations	Oct 3, 2022	Data AugmentationInductive Bias	CodeCode Available	0
Random Data Augmentation based Enhancement: A Generalized Enhancement Approach for Medical Datasets	Oct 3, 2022	Data AugmentationDiagnostic	CodeCode Available	0

Show:10 25 50

← PrevPage 157 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