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 75517600 of 8378 papers

TitleStatusHype
Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks0
Safe Augmentation: Learning Task-Specific Transformations from DataCode0
Salient Slices: Improved Neural Network Training and Performance with Image Entropy0
Segmenting Hyperspectral Images Using Spectral-Spatial Convolutional Neural Networks With Training-Time Data Augmentation0
BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen VideosCode1
Deep Learning for Classification and Severity Estimation of Coffee Leaf Biotic StressCode0
Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization0
A Group-Theoretic Framework for Data AugmentationCode0
Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification0
A CNN-based tool for automatic tongue contour tracking in ultrasound imagesCode0
Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets0
Dr.Quad at MEDIQA 2019: Towards Textual Inference and Question Entailment using contextualized representations0
Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural ImagesCode0
Domain specific cues improve robustness of deep learning based segmentation of ct volumes0
Node Attribute Generation on GraphsCode1
Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent SpaceCode0
Understanding Adversarial Robustness Through Loss Landscape Geometries0
Post-synaptic potential regularization has potentialCode0
A Computer Vision Application for Assessing Facial Acne Severity from Selfie Images0
Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition0
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is ComingCode0
Human Pose Estimation for Real-World Crowded ScenariosCode0
Natural Adversarial ExamplesCode1
Neural Language Model Based Training Data Augmentation for Weakly Supervised Early Rumor DetectionCode0
Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling0
Deep Sequential Mosaicking of Fetoscopic VideosCode0
Multi-hop Federated Private Data Augmentation with Sample Compression0
Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation0
FMRI data augmentation via synthesis0
A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data0
Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue AgentCode0
Affine Disentangled GAN for Interpretable and Robust AV Perception0
The DKU Replay Detection System for the ASVspoof 2019 Challenge: On Data Augmentation, Feature Representation, Classification, and Fusion0
End-to-End Speech Recognition with High-Frame-Rate Features Extraction0
Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning ApplicationsCode0
CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate SpeechCode1
On the Summarization of Consumer Health QuestionsCode0
Improving the Robustness of Question Answering Systems to Question ParaphrasingCode0
Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation0
The University of Sydney's Machine Translation System for WMT190
Effective Rotation-invariant Point CNN with Spherical Harmonics kernelsCode0
Learning Data Augmentation Strategies for Object DetectionCode1
Further advantages of data augmentation on convolutional neural networks0
Mixup of Feature Maps in a Hidden Layer for Training of Convolutional Neural Network0
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 Cities0
A Fourier Perspective on Model Robustness in Computer Vision0
Adversarial Self-Paced Learning for Mixture Models of Hawkes Processes0
Efficient data augmentation using graph imputation neural networks0
Data Interpolating Prediction: Alternative Interpretation of Mixup0
Show:102550
← PrevPage 152 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