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

Showing 78517900 of 8378 papers

TitleStatusHype
Data Augmentation with Manifold Exploring Geometric Transformations for Increased Performance and Robustness0
Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization0
Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation0
Robust and High Performance Face Detector0
Augmentation Scheme for Dealing with Imbalanced Network Traffic Classification Using Deep Learning0
Fully Automatic Segmentation of Sublingual Veins from Retrained U-Net Model for Few Near Infrared Images0
Towards Visible and Thermal Drone Monitoring with Convolutional Neural Networks0
Improving Face Detection Performance with 3D-Rendered Synthetic Data0
Conditional BERT Contextual AugmentationCode0
Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation0
Towards Robust Human Activity Recognition from RGB Video Stream with Limited Labeled Data0
Imitation Learning for End to End Vehicle Longitudinal Control with Forward Camera0
Pretraining by Backtranslation for End-to-end ASR in Low-Resource Settings0
EDF: Ensemble, Distill, and Fuse for Easy Video Labeling0
Deep ChArUco: Dark ChArUco Marker Pose EstimationCode0
Generation of Synthetic Electronic Medical Record Text0
ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape0
Text Data Augmentation Made Simple By Leveraging NLP Cloud APIsCode0
Singing Voice Separation Using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross EntropyCode0
Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation0
Unsupervised Domain Adaptation using Generative Models and Self-ensembling0
Contrastive Learning from Pairwise Measurements0
Tree-Structured Recurrent Switching Linear Dynamical Systems for Multi-Scale ModelingCode0
General-to-Detailed GAN for Infrequent Class Medical ImagesCode0
CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss0
Cross-Lingual Approaches to Reference Resolution in Dialogue Systems0
GANsfer Learning: Combining labelled and unlabelled data for GAN based data augmentation0
Combining High-Level Features of Raw Audio Waves and Mel-Spectrograms for Audio Tagging0
Natural language understanding for task oriented dialog in the biomedical domain in a low resources context0
Data Augmentation using Random Image Cropping and Patching for Deep CNNsCode0
Towards Robust Neural Networks with Lipschitz Continuity0
T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular SamplingCode0
Learning to Detect Instantaneous Changes with Retrospective Convolution and Static Sample Synthesis0
A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural NetworksCode0
Can Synthetic Faces Undo the Damage of Dataset Bias to Face Recognition and Facial Landmark Detection?Code0
Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition0
Transfer Learning with Deep CNNs for Gender Recognition and Age Estimation0
Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern ClassificationCode0
Integrating domain knowledge: using hierarchies to improve deep classifiers0
Detecting Incongruity Between News Headline and Body Text via a Deep Hierarchical EncoderCode0
Deep learning framework DNN with conditional WGAN for protein solubility prediction0
AclNet: efficient end-to-end audio classification CNN0
ProstateGAN: Mitigating Data Bias via Prostate Diffusion Imaging Synthesis with Generative Adversarial Networks0
Deep Neural Network Augmentation: Generating Faces for Affect Analysis0
Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks0
Learning data augmentation policies using augmented random searchCode0
Imagining an Engineer: On GAN-Based Data Augmentation Perpetuating Biases0
ColorUNet: A convolutional classification approach to colorization0
An amplitudes-perturbation data augmentation method in convolutional neural networks for EEG decoding0
Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data AugmentationCode0
Show:102550
← PrevPage 158 of 168Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeiT-B (+MixPro)Accuracy (%)82.9Unverified
2ResNet-200 (DeepAA)Accuracy (%)81.32Unverified
3DeiT-S (+MixPro)Accuracy (%)81.3Unverified
4ResNet-200 (Fast AA)Accuracy (%)80.6Unverified
5ResNet-200 (UA)Accuracy (%)80.4Unverified
6ResNet-200 (AA)Accuracy (%)80Unverified
7ResNet-50 (DeepAA)Accuracy (%)78.3Unverified
8ResNet-50 (TA wide)Accuracy (%)78.07Unverified
9ResNet-50 (LoRot-E)Accuracy (%)77.72Unverified
10ResNet-50 (LoRot-I)Accuracy (%)77.71Unverified
#ModelMetricClaimedVerifiedStatus
1WideResNet-40-2 (Faster AA)Percentage error3.7Unverified
2Shake-Shake (26 2×32d) (Faster AA)Percentage error2.7Unverified
3WideResNet-28-10 (Faster AA)Percentage error2.6Unverified
4Shake-Shake (26 2×112d) (Faster AA)Percentage error2Unverified
5Shake-Shake (26 2×96d) (Faster AA)Percentage error2Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7Unverified
2PaCMAPClassification Accuracy85.3Unverified
3hNNEClassification Accuracy77.4Unverified
4TopoAEClassification Accuracy74.6Unverified