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 3051–3100 of 8378 papers

TitleStatusHype
Inspecting the Geographical Representativeness of Images from Text-to-Image Models—0
RobustFair: Adversarial Evaluation through Fairness Confusion Directed Gradient SearchCode0
BioAug: Conditional Generation based Data Augmentation for Low-Resource Biomedical NERCode0
Boosting Distress Support Dialogue Responses with Motivational Interviewing StrategyCode0
Sharpness & Shift-Aware Self-Supervised Learning—0
Rethinking Data Augmentation for Tabular Data in Deep LearningCode1
An Ensemble Deep Learning Approach for COVID-19 Severity Prediction Using Chest CT ScansCode0
Advising OpenMP Parallelization via a Graph-Based Approach with TransformersCode0
Data Augmentation for Conflict and Duplicate Detection in Software Engineering Sentence Pairs—0
Adversarial Word Dilution as Text Data Augmentation in Low-Resource RegimeCode0
Boosting Event Extraction with Denoised Structure-to-Text Augmentation—0
Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment AnalysisCode1
Learning Better Contrastive View from Radiologist's GazeCode1
t-RAIN: Robust generalization under weather-aliasing label shift attacks—0
Exploiting Frequency Spectrum of Adversarial Images for General Robustness—0
Improved baselines for vision-language pre-training—0
AdamR at SemEval-2023 Task 10: Solving the Class Imbalance Problem in Sexism Detection with Ensemble Learning—0
Learning to Generalize for Cross-domain QACode0
DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-LearningCode1
Consistency Regularization for Domain Generalization with Logit Attribution MatchingCode0
Cloud-RAIN: Point Cloud Analysis with Reflectional InvarianceCode0
SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative ExamplesCode0
Subject-based Non-contrastive Self-Supervised Learning for ECG Signal Processing—0
Improving Small Language Models on PubMedQA via Generative Data Augmentation—0
Uncertainty Estimation and Out-of-Distribution Detection for Deep Learning-Based Image Reconstruction using the Local Lipschitz—0
Cost-efficient Crowdsourcing for Span-based Sequence Labeling: Worker Selection and Data AugmentationCode0
Exploring Zero and Few-shot Techniques for Intent Classification—0
Generation of Structurally Realistic Retinal Fundus Images with Diffusion Models—0
Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design—0
SPSQL: Step-by-step Parsing Based Framework for Text-to-SQL Generation—0
A Survey on the Robustness of Computer Vision Models against Common CorruptionsCode0
Consistent Text Categorization using Data Augmentation in e-Commerce—0
Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution—0
Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm CorruptionsCode0
Code Execution with Pre-trained Language Models—0
Target-Side Augmentation for Document-Level Machine TranslationCode1
Riesz networks: scale invariant neural networks in a single forward pass—0
Graph Masked Autoencoder for Sequential RecommendationCode1
Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization—0
Random Smoothing Regularization in Kernel Gradient Descent Learning—0
Clothes Grasping and Unfolding Based on RGB-D Semantic Segmentation—0
Semantic-aware Generation of Multi-view Portrait DrawingsCode1
Simple Noisy Environment Augmentation for Reinforcement LearningCode0
LatentAugment: Dynamically Optimized Latent Probabilities of Data AugmentationCode0
SeqAug: Sequential Feature Resampling as a modality agnostic augmentation method—0
Improving Contrastive Learning of Sentence Embeddings from AI FeedbackCode1
Multimodal Data Augmentation for Image Captioning using Diffusion ModelsCode0
Real-Time Radiance Fields for Single-Image Portrait View Synthesis—0
Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings—0
Estimating Input Coefficients for Regional Input-Output Tables Using Deep Learning with Mixup—0
Show:102550
← PrevPage 62 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