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 2001–2050 of 8378 papers

TitleStatusHype
Neural Rendering based Urban Scene Reconstruction for Autonomous Driving—0
ExGRG: Explicitly-Generated Relation Graph for Self-Supervised Representation Learning—0
Evaluation Metrics for Text Data Augmentation in NLP—0
Pushing Boundaries: Mixup's Influence on Neural Collapse—0
ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMsCode1
InternLM-Math: Open Math Large Language Models Toward Verifiable ReasoningCode4
Text Role Classification in Scientific Charts Using Multimodal TransformersCode0
A Novel Approach to WaveNet Architecture for RF Signal Separation with Learnable Dilation and Data Augmentation—0
Neural Models for Source Code Synthesis and Completion—0
SoftEDA: Rethinking Rule-Based Data Augmentation with Soft LabelsCode0
AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource RegimesCode0
PAC Learnability under Explanation-Preserving Graph Perturbations—0
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning DatasetCode1
De-amplifying Bias from Differential Privacy in Language Model Fine-tuning—0
CodeIt: Self-Improving Language Models with Prioritized Hindsight ReplayCode1
SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over a Life Science Knowledge GraphCode1
Detection Transformer for Teeth Detection, Segmentation, and Numbering in Oral Rare Diseases: Focus on Data Augmentation and Inpainting Techniques—0
Polyp-DDPM: Diffusion-Based Semantic Polyp Synthesis for Enhanced SegmentationCode1
Improved Generalization of Weight Space Networks via AugmentationsCode0
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language ModelsCode2
Adversarial Data Augmentation for Robust Speaker Verification—0
DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching—0
TimeSiam: A Pre-Training Framework for Siamese Time-Series ModelingCode1
Simulation-Enhanced Data Augmentation for Machine Learning Pathloss Prediction—0
MasonPerplexity at ClimateActivism 2024: Integrating Advanced Ensemble Techniques and Data Augmentation for Climate Activism Stance and Hate Event Identification—0
Diabetes detection using deep learning techniques with oversampling and feature augmentation—0
Position Paper: Assessing Robustness, Privacy, and Fairness in Federated Learning Integrated with Foundation Models—0
A Morphologically-Aware Dictionary-based Data Augmentation Technique for Machine Translation of Under-Represented Languages—0
A Data-Driven Analysis of Robust Automatic Piano Transcription—0
Chameleon: Foundation Models for Fairness-aware Multi-modal Data Augmentation to Enhance Coverage of MinoritiesCode0
Learning Collective Variables with Synthetic Data Augmentation through Physics-Inspired Geodesic InterpolationCode0
Unconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic DataCode0
Augmenting Offline Reinforcement Learning with State-only Interactions—0
Coronary Artery Disease Classification with Different Lesion Degree Ranges based on Deep Learning—0
Data Augmentation Scheme for Raman Spectra with Highly Correlated Annotations—0
Masked Conditional Diffusion Model for Enhancing Deepfake Detection—0
Retrosynthesis prediction enhanced by in-silico reaction data augmentation—0
Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive LearningCode0
Arabic Tweet Act: A Weighted Ensemble Pre-Trained Transformer Model for Classifying Arabic Speech Acts on Twitter—0
Anything in Any Scene: Photorealistic Video Object Insertion—0
Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers—0
Active Generation Network of Human Skeleton for Action Recognition—0
LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field CamerasCode0
ConFit: Improving Resume-Job Matching using Data Augmentation and Contrastive Learning—0
Hybrid Transformer and Spatial-Temporal Self-Supervised Learning for Long-term Traffic Prediction—0
Enhanced Sound Event Localization and Detection in Real 360-degree audio-visual soundscapesCode1
Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning—0
Importance-Aware Data Augmentation for Document-Level Neural Machine Translation—0
A Survey on Data Augmentation in Large Model EraCode2
Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification—0
Show:102550
← PrevPage 41 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