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 8151–8200 of 8378 papers

TitleStatusHype
CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign RecognitionCode0
Exploring the Landscape of Spatial RobustnessCode0
Controllable Top-down Feature Transformer—0
Leaf Identification Using a Deep Convolutional Neural Network—0
Sketching out the Details: Sketch-based Image Retrieval using Convolutional Neural Networks with Multi-stage RegressionCode0
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure—0
Learning from Between-class Examples for Deep Sound RecognitionCode1
Camera Style Adaptation for Person Re-identificationCode0
Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild—0
Adversarial Feature Augmentation for Unsupervised Domain AdaptationCode0
Face Attention Network: An Effective Face Detector for the Occluded FacesCode0
Pseudo-positive regularization for deep person re-identification—0
Learning SO(3) Equivariant Representations with Spherical CNNsCode1
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural NetworksCode0
HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images—0
Learning Compositional Visual Concepts with Mutual Consistency—0
Spectral-spatial classification of hyperspectral images: three tricks and a new supervised learning settingCode0
Invariances and Data Augmentation for Supervised Music TranscriptionCode0
Data Augmentation Generative Adversarial NetworksCode0
Data Augmentation in Emotion Classification Using Generative Adversarial Networks—0
An Exploration of Data Augmentation and RNN Architectures for Question Ranking in Community Question Answering—0
Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels—0
Predicting Users' Negative Feedbacks in Multi-Turn Human-Computer Dialogues—0
Data, Depth, and Design: Learning Reliable Models for Skin Lesion AnalysisCode0
Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice ExtractionCode0
A Bayesian Data Augmentation Approach for Learning Deep ModelsCode0
A Self-Training Method for Semi-Supervised GANs—0
ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection—0
Convolutional Recurrent Neural Networks for Electrocardiogram ClassificationCode0
DocEmul: a Toolkit to Generate Structured Historical DocumentsCode0
Application of Deep Learning in Neuroradiology: Automated Detection of Basal Ganglia Hemorrhage using 2D-Convolutional Neural Networks—0
Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep ChemometricsCode0
Machine Learning Models that Remember Too MuchCode0
ExprGAN: Facial Expression Editing with Controllable Expression IntensityCode0
NiftyNet: a deep-learning platform for medical imagingCode1
Globally Normalized ReaderCode0
Learning to Compose Domain-Specific Transformations for Data AugmentationCode0
Assessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution—0
Incorporating Metadata into Content-Based User Embeddings—0
Data Augmentation for Visual Question Answering—0
Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder—0
DeepPrior++: Improving Fast and Accurate 3D Hand Pose EstimationCode0
A Compromise Principle in Deep Monocular Depth Estimation—0
Deep Learning for Target Classification from SAR Imagery: Data Augmentation and Translation InvarianceCode0
Learning a 3D descriptor for cross-source point cloud registration from synthetic data—0
Leaf Counting with Deep Convolutional and Deconvolutional NetworksCode0
Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D RepresentationsCode0
Improving Deep Learning using Generic Data Augmentation—0
DeepBreath: Deep Learning of Breathing Patterns for Automatic Stress Recognition using Low-Cost Thermal Imaging in Unconstrained SettingsCode0
Applying Data Augmentation to Handwritten Arabic Numeral Recognition Using Deep Learning Neural Networks—0
Show:102550
← PrevPage 164 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