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 3201–3250 of 8378 papers

TitleStatusHype
Topology-Guided Multi-Class Cell Context Generation for Digital Pathology—0
DRAC: Diabetic Retinopathy Analysis Challenge with Ultra-Wide Optical Coherence Tomography Angiography Images—0
What Affects Learned Equivariance in Deep Image Recognition Models?—0
Performance of Data Augmentation Methods for Brazilian Portuguese Text Classification—0
DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic SegmentationCode1
Learning Stage-wise GANs for Whistle Extraction in Time-Frequency SpectrogramsCode0
A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection—0
FakET: Simulating Cryo-Electron Tomograms with Neural Style TransferCode1
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
Cross-modal tumor segmentation using generative blending augmentation and self trainingCode0
On the Variance of Neural Network Training with respect to Test Sets and Distributions—0
PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification—0
Robustness Benchmark of Road User Trajectory Prediction Models for Automated Driving—0
Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object DetectionCode1
Astroformer: More Data Might not be all you need for ClassificationCode1
A Guide for Practical Use of ADMG Causal Data AugmentationCode0
Multi-Modal Representation Learning with Text-Driven Soft Masks—0
D-Score: A White-Box Diagnosis Score for CNNs Based on Mutation Operators—0
Better Language Models of Code through Self-ImprovementCode0
Fair-CDA: Continuous and Directional Augmentation for Group Fairness—0
Simple Domain Generalization Methods are Strong Baselines for Open Domain GeneralizationCode0
No Place to Hide: Dual Deep Interaction Channel Network for Fake News Detection based on Data Augmentation—0
Traffic Sign Recognition Dataset and Data AugmentationCode0
Improving extreme weather events detection with light-weight neural networks—0
One-shot Unsupervised Domain Adaptation with Personalized Diffusion ModelsCode1
Synthesis of Mathematical programs from Natural Language Specifications—0
FairGen: Towards Fair Graph Generation—0
Mixed Autoencoder for Self-supervised Visual Representation LearningCode1
ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and LocalizationCode0
Model-agnostic explainable artificial intelligence for object detection in image dataCode0
WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion ModelsCode1
AraSpot: Arabic Spoken Command SpottingCode0
Hard Regularization to Prevent Deep Online Clustering Collapse without Data AugmentationCode0
De-coupling and De-positioning Dense Self-supervised LearningCode0
Improving the Transferability of Adversarial Samples by Path-Augmented MethodCode1
Efficient Deep Learning of Robust, Adaptive Policies using Tube MPC-Guided Data Augmentation—0
Unsupervised Pre-Training For Data-Efficient Text-to-Speech On Low Resource LanguagesCode1
EEGMatch: Learning with Incomplete Labels for Semi-Supervised EEG-based Cross-Subject Emotion RecognitionCode1
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling—0
Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example AttacksCode1
Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation—0
VisDA 2022 Challenge: Domain Adaptation for Industrial Waste SortingCode1
Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability—0
SASS: Data and Methods for Subject Aware Sentence Simplification—0
Deep Augmentation: Self-Supervised Learning with Transformations in Activation Space—0
Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching—0
Improved Adversarial Training Through Adaptive Instance-wise Loss SmoothingCode0
DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling—0
Towards Diverse and Coherent Augmentation for Time-Series ForecastingCode1
Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning—0
Show:102550
← PrevPage 65 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