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 7351–7400 of 8378 papers

TitleStatusHype
Adversarial AutoAugment—0
Fully Automated Multi-Organ Segmentation in Abdominal Magnetic Resonance Imaging with Deep Neural Networks—0
end-to-end training of a large vocabulary end-to-end speech recognition system—0
A Deep Learning Model for Chilean Bills ClassificationCode0
Data Augmentation by AutoEncoders for Unsupervised Anomaly Detection—0
AEGR: A simple approach to gradient reversal in autoencoders for network anomaly detection—0
The State of Knowledge Distillation for ClassificationCode0
Triple Generative Adversarial NetworksCode0
Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems—0
LSTM-TDNN with convolutional front-end for Dialect Identification in the 2019 Multi-Genre Broadcast Challenge—0
LS-Net: Fast Single-Shot Line-Segment Detector—0
Benchmark for Generic Product Detection: A Low Data Baseline for Dense Object DetectionCode0
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration—0
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking—0
Data augmentation approaches for improving animal audio classification—0
Joint Learning of Generative Translator and Classifier for Visually Similar Classes—0
Training without training data: Improving the generalizability of automated medical abbreviation disambiguation—0
Deep Learning-based Denoising of Mammographic Images using Physics-driven Data Augmentation—0
The Wasserstein-Fourier Distance for Stationary Time SeriesCode0
Audiogmenter: a MATLAB Toolbox for Audio Data AugmentationCode0
Multimodal Self-Supervised Learning for Medical Image Analysis—0
Parting with Illusions about Deep Active Learning—0
Medication Regimen Extraction From Medical Conversations—0
What You See is What You Get: Exploiting Visibility for 3D Object DetectionCode0
DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images—0
Inception Architecture and Residual Connections in Classification of Breast Cancer Histology Images—0
Bias Remediation in Driver Drowsiness Detection systems using Generative Adversarial Networks—0
libmolgrid: GPU Accelerated Molecular Gridding for Deep Learning ApplicationsCode0
Selective Synthetic Augmentation with Quality Assurance—0
Goal-Conditioned Variational Autoencoder Trajectory Primitives with Continuous and Discrete Latent Codes—0
Automatic Financial Feature Construction—0
VideoDG: Generalizing Temporal Relations in Videos to Novel DomainsCode0
Explaining Sequence-Level Knowledge Distillation as Data-Augmentation for Neural Machine Translation—0
A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification—0
Data Augmentation for Deep Learning-based Radio Modulation Classification—0
Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue—0
Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation—0
An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering—0
Let's Get Dirty: GAN Based Data Augmentation for Camera Lens Soiling Detection in Autonomous Driving—0
A deep learning based tool for automatic brain extraction from functional magnetic resonance images in rodentsCode0
Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition—0
Just Ask:An Interactive Learning Framework for Vision and Language Navigation—0
Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces—0
Scalable Deep Generative Relational Model with High-Order Node DependenceCode0
Mean Shift Rejection: Training Deep Neural Networks Without Minibatch Statistics or Normalization—0
A Multilayered Block Network Model to Forecast Large Dynamic Transportation Graphs: an Application to US Air Transport—0
Augmentation Methods on Monophonic Audio for Instrument Classification in Polyphonic MusicCode0
E-Stitchup: Data Augmentation for Pre-Trained Embeddings—0
Patch Reordering: a Novel Way to Achieve Rotation and Translation Invariance in Convolutional Neural Networks—0
Data Augmentation Using Adversarial Training for Construction-Equipment Classification—0
Show:102550
← PrevPage 148 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