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 3401–3450 of 8378 papers

TitleStatusHype
Bag of Tricks for In-Distribution Calibration of Pretrained TransformersCode0
Improving Recommendation Fairness via Data AugmentationCode1
Finetuning Is a Surprisingly Effective Domain Adaptation Baseline in Handwriting Recognition—0
Joint Span Segmentation and Rhetorical Role Labeling with Data Augmentation for Legal Documents—0
Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex OptimizationCode0
Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns—0
CUDA: Curriculum of Data Augmentation for Long-Tailed RecognitionCode1
Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization—0
Toward Degree Bias in Embedding-Based Knowledge Graph CompletionCode1
Evaluation of Data Augmentation and Loss Functions in Semantic Image Segmentation for Drilling Tool Wear DetectionCode0
Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information—0
Augmenting NLP data to counter Annotation Artifacts for NLI Tasks—0
MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint DetectionCode0
One-shot Visual Imitation via Attributed Waypoints and Demonstration Augmentation—0
Data Augmentation for Robust Character Detection in Fantasy NovelsCode0
Mask Conditional Synthetic Satellite ImageryCode1
Effective Data Augmentation With Diffusion ModelsCode2
Improving CT Image Segmentation Accuracy Using StyleGAN Driven Data Augmentation—0
IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning—0
OSRT: Omnidirectional Image Super-Resolution with Distortion-aware TransformerCode1
Data augmentation for machine learning of chemical process flowsheets—0
Industrial computed tomography based intelligent non-destructive testing method for power capacitor—0
Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link PredictionCode1
GAT: Guided Adversarial Training with Pareto-optimal Auxiliary TasksCode0
The SSL Interplay: Augmentations, Inductive Bias, and Generalization—0
MAC: A unified framework boosting low resource automatic speech recognition—0
Exploring Data Augmentation for Code Generation TasksCode0
Adversarial Learning Data Augmentation for Graph Contrastive Learning in RecommendationCode0
Latent Space Bayesian Optimization with Latent Data Augmentation for Enhanced Exploration—0
CIPER: Combining Invariant and Equivariant Representations Using Contrastive and Predictive Learning—0
Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics—0
This Intestine Does Not Exist: Multiscale Residual Variational Autoencoder for Realistic Wireless Capsule Endoscopy Image Generation—0
Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints—0
Contrastive Learning with Consistent RepresentationsCode0
Mitigating Data Scarcity for Large Language ModelsCode0
How to choose "Good" Samples for Text Data Augmentation—0
Neural Network Architecture for Database Augmentation Using Shared FeaturesCode0
LesionAid: Vision Transformers-based Skin Lesion Generation and Classification—0
Exploring Invariant Representation for Visible-Infrared Person Re-Identification—0
Domain Generalization Emerges from Dreaming—0
Deep COVID-19 Forecasting for Multiple States with Data Augmentation—0
A Bayesian Generative Adversarial Network (GAN) to Generate Synthetic Time-Series Data, Application in Combined Sewer Flow Prediction—0
Rethinking Soft Label in Label Distribution Learning Perspective—0
PointSmile: Point Self-supervised Learning via Curriculum Mutual Information—0
Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation PoliciesCode0
PromptMix: Text-to-image diffusion models enhance the performance of lightweight networks—0
Standardized CycleGAN training for unsupervised stain adaptation in invasive carcinoma classification for breast histopathology—0
Fast-BEV: A Fast and Strong Bird's-Eye View Perception BaselineCode2
Long-Term Modeling of Financial Machine Learning for Active Portfolio Management—0
The Influences of Color and Shape Features in Visual Contrastive Learning—0
Show:102550
← PrevPage 69 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