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 701–750 of 8378 papers

TitleStatusHype
SE-GCL: An Event-Based Simple and Effective Graph Contrastive Learning for Text Representation—0
AD-LLM: Benchmarking Large Language Models for Anomaly DetectionCode1
Understanding and Mitigating Memorization in Diffusion Models for Tabular Data—0
Facial Surgery Preview Based on the Orthognathic Treatment Prediction—0
Learning Normal Flow Directly From Event NeighborhoodsCode1
Deep Learning Models for Colloidal Nanocrystal SynthesisCode0
ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training DataCode1
Enhancement of text recognition for hanja handwritten documents of Ancient Korea—0
APAR: Modeling Irregular Target Functions in Tabular Regression via Arithmetic-Aware Pre-Training and Adaptive-Regularized Fine-TuningCode0
Fully Test-time Adaptation for Tabular Data—0
SegHeD+: Segmentation of Heterogeneous Data for Multiple Sclerosis Lesions with Anatomical Constraints and Lesion-aware Augmentation—0
Who's the (Multi-)Fairest of Them All: Rethinking Interpolation-Based Data Augmentation Through the Lens of MulticalibrationCode0
FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image DenoisingCode1
One Node One Model: Featuring the Missing-Half for Graph ClusteringCode0
AMuSeD: An Attentive Deep Neural Network for Multimodal Sarcasm Detection Incorporating Bi-modal Data Augmentation—0
Comparative Analysis of Mel-Frequency Cepstral Coefficients and Wavelet Based Audio Signal Processing for Emotion Detection and Mental Health Assessment in Spoken Speech—0
Exemplar Masking for Multimodal Incremental LearningCode0
First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI—0
PolyIPA -- Multilingual Phoneme-to-Grapheme Conversion Model—0
Residual Channel Boosts Contrastive Learning for Radio Frequency Fingerprint Identification—0
Vision Transformers for Efficient Indoor Pathloss Radio Map Prediction—0
BDA: Bangla Text Data Augmentation FrameworkCode0
A Physics-based Generative Model to Synthesize Training Datasets for MRI-based Fat Quantification—0
LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information—0
Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentation—0
AGMixup: Adaptive Graph Mixup for Semi-supervised Node ClassificationCode0
Augmenting Sequential Recommendation with Balanced Relevance and DiversityCode1
DAKD: Data Augmentation and Knowledge Distillation using Diffusion Models for SAR Oil Spill Segmentation—0
Fast Mixing of Data Augmentation Algorithms: Bayesian Probit, Logit, and Lasso RegressionCode0
Comparative Opinion Mining in Product Reviews: Multi-perspective Prompt-based Learning—0
Can We Generate Visual Programs Without Prompting LLMs?—0
NLPineers@ NLU of Devanagari Script Languages 2025: Hate Speech Detection using Ensembling of BERT-based modelsCode0
Generative Modeling and Data Augmentation for Power System Production SimulationCode0
Multi-Scale Contrastive Learning for Video Temporal Grounding—0
Bayesian Data Augmentation and Training for Perception DNN in Autonomous Aerial VehiclesCode0
Leveraging Content and Context Cues for Low-Light Image EnhancementCode0
A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack DetectionCode0
Improving the Natural Language Inference robustness to hard dataset by data augmentation and preprocessing—0
CoPrUS: Consistency Preserving Utterance Synthesis towards more realistic benchmark dialoguesCode0
Optimizing Alignment with Less: Leveraging Data Augmentation for Personalized Evaluation—0
Data Augmentation with Variational Autoencoder for Imbalanced DatasetCode0
HSDA: High-frequency Shuffle Data Augmentation for Bird's-Eye-View Map SegmentationCode0
SGIA: Enhancing Fine-Grained Visual Classification with Sequence Generative Image Augmentation—0
World-Consistent Data Generation for Vision-and-Language Navigation—0
MIMO Detection under Hardware Impairments: Data Augmentation With Boosting—0
SQ-Whisper: Speaker-Querying based Whisper Model for Target-Speaker ASRCode0
Comprehensive Evaluation of Multimodal AI Models in Medical Imaging Diagnosis: From Data Augmentation to Preference-Based Comparison—0
UNet++ and LSTM combined approach for Breast Ultrasound Image Segmentation—0
Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Images—0
Building a Family of Data Augmentation Models for Low-cost LLM Fine-tuning on the Cloud—0
Show:102550
← PrevPage 15 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