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 7601–7650 of 8378 papers

TitleStatusHype
Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks—0
Greedy AutoAugmentCode0
GANs 'N Lungs: improving pneumonia prediction—0
Fill the GAP: Exploiting BERT for Pronoun ResolutionCode0
Robustifying deep networks for image segmentation—0
Baidu Neural Machine Translation Systems for WMT19—0
A Survey on Deep Learning of Small Sample in Biomedical Image AnalysisCode0
Team JUST at the MADAR Shared Task on Arabic Fine-Grained Dialect Identification—0
Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks—0
Safe Augmentation: Learning Task-Specific Transformations from DataCode0
Salient Slices: Improved Neural Network Training and Performance with Image Entropy—0
Segmenting Hyperspectral Images Using Spectral-Spatial Convolutional Neural Networks With Training-Time Data Augmentation—0
Deep Learning for Classification and Severity Estimation of Coffee Leaf Biotic StressCode0
A Group-Theoretic Framework for Data AugmentationCode0
Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization—0
A CNN-based tool for automatic tongue contour tracking in ultrasound imagesCode0
Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification—0
Domain specific cues improve robustness of deep learning based segmentation of ct volumes—0
Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets—0
Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural ImagesCode0
Dr.Quad at MEDIQA 2019: Towards Textual Inference and Question Entailment using contextualized representations—0
Understanding Adversarial Robustness Through Loss Landscape Geometries—0
Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent SpaceCode0
Post-synaptic potential regularization has potentialCode0
A Computer Vision Application for Assessing Facial Acne Severity from Selfie Images—0
Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition—0
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is ComingCode0
Neural Language Model Based Training Data Augmentation for Weakly Supervised Early Rumor DetectionCode0
Human Pose Estimation for Real-World Crowded ScenariosCode0
Deep Sequential Mosaicking of Fetoscopic VideosCode0
Multi-hop Federated Private Data Augmentation with Sample Compression—0
Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling—0
Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation—0
FMRI data augmentation via synthesis—0
A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data—0
Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue AgentCode0
Affine Disentangled GAN for Interpretable and Robust AV Perception—0
The DKU Replay Detection System for the ASVspoof 2019 Challenge: On Data Augmentation, Feature Representation, Classification, and Fusion—0
End-to-End Speech Recognition with High-Frame-Rate Features Extraction—0
Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning ApplicationsCode0
Improving the Robustness of Question Answering Systems to Question ParaphrasingCode0
On the Summarization of Consumer Health QuestionsCode0
Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation—0
The University of Sydney's Machine Translation System for WMT19—0
Effective Rotation-invariant Point CNN with Spherical Harmonics kernelsCode0
Further advantages of data augmentation on convolutional neural networks—0
Mixup of Feature Maps in a Hidden Layer for Training of Convolutional Neural Network—0
Bias Correction of Learned Generative Models using Likelihood-Free Importance WeightingCode0
Detection of Myocardial Infarction Based on Novel Deep Transfer Learning Methods for Urban Healthcare in Smart Cities—0
A Fourier Perspective on Model Robustness in Computer Vision—0
Show:102550
← PrevPage 153 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