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 79518000 of 8378 papers

TitleStatusHype
In Defense of Single-column Networks for Crowd Counting0
Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks0
Egocentric Gesture Recognition for Head-Mounted AR devices0
Learning Invariances using the Marginal Likelihood0
Deep Learning using K-space Based Data Augmentation for Automated Cardiac MR Motion Artefact Detection0
GestureGAN for Hand Gesture-to-Gesture Translation in the WildCode0
Automatic Airway Segmentation in chest CT using Convolutional Neural Networks0
Automatic Plaque Detection in IVOCT Pullbacks Using Convolutional Neural Networks0
A Semi-Supervised Data Augmentation Approach using 3D Graphical EnginesCode0
Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer0
ODSQA: Open-domain Spoken Question Answering DatasetCode0
Data augmentation using synthetic data for time series classification with deep residual networksCode0
Normalization Before Shaking Toward Learning Symmetrically Distributed Representation Without Margin in Speech Emotion Recognition0
Identifying Aggression and Toxicity in Comments using Capsule Network0
Aggression Detection in Social Media: Using Deep Neural Networks, Data Augmentation, and Pseudo Labeling0
Aggression Identification Using Deep Learning and Data AugmentationCode0
Data Augmentation for Robust Keyword Spotting under Playback Interference0
Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks0
Gender Privacy: An Ensemble of Semi Adversarial Networks for Confounding Arbitrary Gender Classifiers0
ARM: Augment-REINFORCE-Merge Gradient for Stochastic Binary NetworksCode0
Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speech0
Back-Translation-Style Data Augmentation for End-to-End ASR0
Characters Detection on Namecard with faster RCNN0
Deep Learning Methods and Applications for Region of Interest Detection in Dermoscopic Images0
Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks0
Pythia v0.1: the Winning Entry to the VQA Challenge 2018Code3
ISIC 2017 Skin Lesion Segmentation Using Deep Encoder-Decoder Network0
MVDepthNet: Real-time Multiview Depth Estimation Neural NetworkCode0
Automatic Speech Recognition for Humanitarian Applications in Somali0
Improving Automatic Skin Lesion Segmentation using Adversarial Learning based Data Augmentation0
Conditional Infilling GANs for Data Augmentation in Mammogram ClassificationCode0
Monocular Object Orientation Estimation using Riemannian Regression and Classification NetworksCode0
Bio-Measurements Estimation and Support in Knee Recovery through Machine Learning0
Modeling Visual Context is Key to Augmenting Object Detection DatasetsCode0
Robust Deep Multi-modal Learning Based on Gated Information Fusion Network0
Learning Noise-Invariant Representations for Robust Speech Recognition0
A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic SegmentationCode0
Deep neural network ensemble by data augmentation and bagging for skin lesion classification0
Semi-supervised Feature Learning For Improving Writer Identification0
Neural Networks Regularization Through Representation LearningCode0
Subsampled Turbulence Removal Network0
Hydranet: Data Augmentation for Regression Neural Networks0
Deep semi-supervised segmentation with weight-averaged consistency targets0
Deep Learning Hyperspectral Image Classification Using Multiple Class-based Denoising Autoencoders, Mixed Pixel Training Augmentation, and Morphological Operations0
High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks0
Data Augmentation for Detection of Architectural Distortion in Digital Mammography using Deep Learning Approach0
Sequence-to-Sequence Data Augmentation for Dialogue Language UnderstandingCode0
HAMLET: Hierarchical Harmonic Filters for Learning Tracts from Diffusion MRI0
Learning under selective labels in the presence of expert consistency0
Dependent Relational Gamma Process Models for Longitudinal Networks0
Show:102550
← PrevPage 160 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