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 951–1000 of 8378 papers

TitleStatusHype
Augmentation Policy Generation for Image Classification Using Large Language Models—0
Deep Generative Models Unveil Patterns in Medical Images Through Vision-Language ConditioningCode0
Computational Approaches to Arabic-English Code-Switching—0
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided DiffusionCode1
REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models—0
A Survey on Data Synthesis and Augmentation for Large Language Models—0
Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations—0
Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous ControlCode0
Comparative Analysis of Extrinsic Factors for NER in French—0
SDI-Paste: Synthetic Dynamic Instance Copy-Paste for Video Instance Segmentation—0
Synthetic Augmentation for Anatomical Landmark Localization using DDPMs—0
Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look—0
Xeno-learning: knowledge transfer across species in deep learning-based spectral image analysis—0
AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG taskCode0
YOLO-ELA: Efficient Local Attention Modeling for High-Performance Real-Time Insulator Defect Detection—0
Optimizing Encoder-Only Transformers for Session-Based Recommendation Systems—0
Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models—0
Towards Fair Graph Representation Learning in Social Networks—0
Time Series Viewmakers for Robust Disruption Prediction—0
Graph Masked Autoencoder for Spatio-Temporal Graph Learning—0
Fake it till you predict it: data augmentation strategies to detect initiation and termination of oncology treatment—0
Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for ClassificationCode0
Joint Mixing Data Augmentation for Skeleton-based Action RecognitionCode0
Diabetic retinopathy image classification method based on GreenBen data augmentation—0
Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal HealthCode0
Intent-Enhanced Data Augmentation for Sequential Recommendation—0
HpEIS: Learning Hand Pose Embeddings for Multimedia Interactive Systems—0
MYCROFT: Towards Effective and Efficient External Data Augmentation—0
A Target-Aware Analysis of Data Augmentation for Hate Speech Detection—0
The Effects of Hallucinations in Synthetic Training Data for Relation Extraction—0
Minority-Focused Text-to-Image Generation via Prompt OptimizationCode1
Disease Entity Recognition and Normalization is Improved with Large Language Model Derived Synthetic Normalized Mentions—0
Explainability of Deep Neural Networks for Brain Tumor DetectionCode0
Unsupervised Data Validation Methods for Efficient Model Training—0
Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion ModelsCode0
Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare—0
When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario ContextCode0
TinyClick: Single-Turn Agent for Empowering GUI Automation—0
Zero-Shot Generalization of Vision-Based RL Without Data Augmentation—0
CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages—0
MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-ResolutionCode0
Transesophageal Echocardiography Generation using Anatomical Models—0
Clean Evaluations on Contaminated Visual Language Models—0
ELMO: Enhanced Real-time LiDAR Motion Capture through Upsampling—0
Improving Data Augmentation-based Cross-Speaker Style Transfer for TTS with Singing Voice, Style Filtering, and F0 MatchingCode4
Adaptive Label Smoothing for Out-of-Distribution Detection—0
SymDiff: Equivariant Diffusion via Stochastic Symmetrisation—0
Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga—0
HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian AidCode0
Collapsed Language Models Promote FairnessCode0
Show:102550
← PrevPage 20 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