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 2451–2500 of 8378 papers

TitleStatusHype
A Persuasion-Based Prompt Learning Approach to Improve Smishing Detection through Data Augmentation—0
DFlow: Diverse Dialogue Flow Simulation with Large Language Models—0
Fine-Tuning Pre-trained Language Models for Robust Causal Representation Learning—0
How Does Data Diversity Shape the Weight Landscape of Neural Networks?—0
Augmentation Policy Generation for Image Classification Using Large Language Models—0
FaceSaliencyAug: Mitigating Geographic, Gender and Stereotypical Biases via Saliency-Based Data Augmentation—0
Computational Approaches to Arabic-English Code-Switching—0
STCON System for the CHiME-8 Challenge—0
Deep Generative Models Unveil Patterns in Medical Images Through Vision-Language ConditioningCode0
A Survey on Data Synthesis and Augmentation for Large Language Models—0
Comparative Analysis of Extrinsic Factors for NER in French—0
REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models—0
SDI-Paste: Synthetic Dynamic Instance Copy-Paste for Video Instance Segmentation—0
Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations—0
Synthetic Augmentation for Anatomical Landmark Localization using DDPMs—0
Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look—0
Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous ControlCode0
Optimizing Encoder-Only Transformers for Session-Based Recommendation Systems—0
AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG taskCode0
Towards Fair Graph Representation Learning in Social Networks—0
Xeno-learning: knowledge transfer across species in deep learning-based spectral image analysis—0
YOLO-ELA: Efficient Local Attention Modeling for High-Performance Real-Time Insulator Defect Detection—0
Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models—0
Time Series Viewmakers for Robust Disruption Prediction—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
Graph Masked Autoencoder for Spatio-Temporal Graph Learning—0
Joint Mixing Data Augmentation for Skeleton-based Action RecognitionCode0
Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal HealthCode0
Diabetic retinopathy image classification method based on GreenBen data augmentation—0
Intent-Enhanced Data Augmentation for Sequential Recommendation—0
MYCROFT: Towards Effective and Efficient External Data Augmentation—0
HpEIS: Learning Hand Pose Embeddings for Multimedia Interactive Systems—0
A Target-Aware Analysis of Data Augmentation for Hate Speech Detection—0
Unsupervised Data Validation Methods for Efficient Model Training—0
Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion ModelsCode0
Explainability of Deep Neural Networks for Brain Tumor DetectionCode0
The Effects of Hallucinations in Synthetic Training Data for Relation Extraction—0
When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario ContextCode0
Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare—0
Disease Entity Recognition and Normalization is Improved with Large Language Model Derived Synthetic Normalized Mentions—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
Zero-Shot Generalization of Vision-Based RL Without Data Augmentation—0
TinyClick: Single-Turn Agent for Empowering GUI Automation—0
ELMO: Enhanced Real-time LiDAR Motion Capture through Upsampling—0
Adaptive Label Smoothing for Out-of-Distribution Detection—0
SymDiff: Equivariant Diffusion via Stochastic Symmetrisation—0
Show:102550
← PrevPage 50 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