SOTAVerified

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.

Further readings:

( Image credit: Albumentations )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4901–4950 of 8378 papers

TitleStatusHype
Syntax-based data augmentation for Hungarian-English machine translationCode0
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation—0
Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning—0
MODALS: Data augmentation that works for everyone—0
AugLy: Data Augmentations for RobustnessCode5
Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies—0
Improving Robustness in Multilingual Machine Translation via Data Augmentation—0
SUBS: Subtree Substitution for Compositional Semantic Parsing—0
Data Augmentation for Low-Resource Dialogue Summarization—0
Sentence-Level Resampling for Named Entity Recognition—0
Label-guided Data Augmentation for Prompt-based Few Shot Learners—0
Product Answer Generation from Heterogeneous Sources: A New Benchmark and Best Practices—0
Improving Data Augmentation in Low-resource Question Answering with Active Learning in Multiple Stages—0
Enhancing Robustness in Aspect-based Sentiment Analysis by Better Exploiting Data Augmentation—0
Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework—0
Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning—0
Data Augmentation for Biomedical Factoid Question Answering—0
DG2: Data Augmentation Through Document Grounded Dialogue Generation—0
Improving negation detection with negation-focused pre-training—0
SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative SamplesCode1
Recent Progress in the CUHK Dysarthric Speech Recognition System—0
Time Series Generation with Masked AutoencoderCode1
ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization—0
Investigation of Data Augmentation Techniques for Disordered Speech Recognition—0
Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition—0
Making a (Counterfactual) Difference One Rationale at a TimeCode0
Multi-task Pre-training Language Model for Semantic Network CompletionCode0
On Adversarial Robustness of Trajectory Prediction for Autonomous VehiclesCode1
VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting—0
Data augmentation through multivariate scenario forecasting in Data Centers using Generative Adversarial NetworksCode0
Motion-Focused Contrastive Learning of Video RepresentationsCode1
Learning Fair Node Representations with Graph Counterfactual FairnessCode1
MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images—0
Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks—0
Model-Based Image Signal Processors via Learnable Dictionaries—0
Iterative training of robust k-space interpolation networks for improved image reconstruction with limited scan specific training samples—0
A study on cross-corpus speech emotion recognition and data augmentation—0
Invariance encoding in sliced-Wasserstein space for image classification with limited training dataCode0
Semantic-based Data Augmentation for Math Word Problems—0
Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition—0
GenLabel: Mixup Relabeling using Generative Models—0
Uncertainty-Aware Cascaded Dilation Filtering for High-Efficiency DerainingCode1
A 1D CNN for high accuracy classification and transfer learning in motor imagery EEG-based brain-computer interfaceCode1
EM-driven unsupervised learning for efficient motion segmentationCode1
Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection—0
FROTE: Feedback Rule-Driven Oversampling for Editing Models—0
AutoBalance: Optimized Loss Functions for Imbalanced DataCode1
Data Augmentation for Depression Detection Using Skeleton-Based Gait Information—0
Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy ClassificationCode0
Learning to Generate Novel Classes for Deep Metric Learning—0
Show:102550
← PrevPage 99 of 168Next →
All datasetsImageNetCIFAR-10GA1457

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeiT-B (+MixPro)Accuracy (%)82.9—Unverified
2ResNet-200 (DeepAA)Accuracy (%)81.32—Unverified
3DeiT-S (+MixPro)Accuracy (%)81.3—Unverified
4ResNet-200 (Fast AA)Accuracy (%)80.6—Unverified
5ResNet-200 (UA)Accuracy (%)80.4—Unverified
6ResNet-200 (AA)Accuracy (%)80—Unverified
7ResNet-50 (DeepAA)Accuracy (%)78.3—Unverified
8ResNet-50 (TA wide)Accuracy (%)78.07—Unverified
9ResNet-50 (LoRot-E)Accuracy (%)77.72—Unverified
10ResNet-50 (LoRot-I)Accuracy (%)77.71—Unverified
#ModelMetricClaimedVerifiedStatus
1WideResNet-40-2 (Faster AA)Percentage error3.7—Unverified
2Shake-Shake (26 2×32d) (Faster AA)Percentage error2.7—Unverified
3WideResNet-28-10 (Faster AA)Percentage error2.6—Unverified
4Shake-Shake (26 2×112d) (Faster AA)Percentage error2—Unverified
5Shake-Shake (26 2×96d) (Faster AA)Percentage error2—Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7—Unverified
2PaCMAPClassification Accuracy85.3—Unverified
3hNNEClassification Accuracy77.4—Unverified
4TopoAEClassification Accuracy74.6—Unverified