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 2401–2450 of 8378 papers

TitleStatusHype
Scaling-based Data Augmentation for Generative Models and its Theoretical Extension—0
Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models—0
Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification—0
BongLLaMA: LLaMA for Bangla Language—0
LinFormer: A Linear-based Lightweight Transformer Architecture For Time-Aware MIMO Channel Prediction—0
Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector QuantizationCode0
Guiding Through Complexity: What Makes Good Supervision for Hard Reasoning Tasks?Code0
Evaluating Neural Networks for Early Maritime Threat Detection—0
Your Image is Secretly the Last Frame of a Pseudo Video—0
CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCoCode0
SAFE setup for generative molecular design—0
On Occlusions in Video Action Detection: Benchmark Datasets And Training RecipesCode0
Towards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches—0
Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social MediaCode0
Ali-AUG: Innovative Approaches to Labeled Data Augmentation using One-Step Diffusion Model—0
Perturbation-based Graph Active Learning for Weakly-Supervised Belief Representation Learning—0
CapsuleNet: A Deep Learning Model To Classify GI Diseases Using EfficientNet-b7Code0
Can Self Supervision Rejuvenate Similarity-Based Link Prediction?—0
An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation—0
Evaluating and Improving Automatic Speech Recognition Systems for Korean Meteorological Experts—0
GADT: Enhancing Transferable Adversarial Attacks through Gradient-guided Adversarial Data Transformation—0
Improving Model Factuality with Fine-grained Critique-based Evaluator—0
Data Augmentation for Automated Adaptive Rodent Training—0
FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive LearningCode0
Bridging the Gaps: Utilizing Unlabeled Face Recognition Datasets to Boost Semi-Supervised Facial Expression RecognitionCode0
Together We Can: Multilingual Automatic Post-Editing for Low-Resource LanguagesCode0
Unsupervised Domain Adaptation for Action Recognition via Self-Ensembling and Conditional Embedding Alignment—0
NucleiMix: Realistic Data Augmentation for Nuclei Instance Segmentation—0
Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap—0
Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence—0
Scalable Implicit Graphon LearningCode0
CK4Gen: A Knowledge Distillation Framework for Generating High-Utility Synthetic Survival Datasets in Healthcare—0
Masked Clinical Modelling: A Framework for Synthetic and Augmented Survival Data Generation—0
SaVe-TAG: Semantic-aware Vicinal Risk Minimization for Long-Tailed Text-Attributed Graphs—0
Polyp-E: Benchmarking the Robustness of Deep Segmentation Models via Polyp Editing—0
PGCS: Physical Law embedded Generative Cloud Synthesis in Remote Sensing ImagesCode0
Efficient Neural Network Training via Subset Pretraining—0
ToW: Thoughts of Words Improve Reasoning in Large Language ModelsCode0
An Explainable Contrastive-based Dilated Convolutional Network with Transformer for Pediatric Pneumonia Detection—0
Deep Learning and Data Augmentation for Detecting Self-Admitted Technical DebtCode0
Habaek: High-performance water segmentation through dataset expansion and inductive bias optimizationCode0
Data Augmentation of Multivariate Sensor Time Series using Autoregressive Models and Application to Failure Prognostics—0
Towards Combating Frequency Simplicity-biased Learning for Domain GeneralizationCode0
LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Space—0
KTCR: Improving Implicit Hate Detection with Knowledge Transfer driven Concept Refinement—0
Data Augmentation via Diffusion Model to Enhance AI Fairness—0
Cutting-Edge Detection of Fatigue in Drivers: A Comparative Study of Object Detection Models—0
AugInsert: Learning Robust Visual-Force Policies via Data Augmentation for Object Assembly Tasks—0
DFlow: Diverse Dialogue Flow Simulation with Large Language Models—0
A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models—0
Show:102550
← PrevPage 49 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