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 7501–7550 of 8378 papers

TitleStatusHype
A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages—0
Personalization of Deep Learning—0
An Active Learning Approach for Reducing Annotation Cost in Skin Lesion AnalysisCode0
An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detectorCode0
PASS3D: Precise and Accelerated Semantic Segmentation for 3D Point Cloud—0
Deep Esophageal Clinical Target Volume Delineation using Encoded 3D Spatial Context of Tumors, Lymph Nodes, and Organs At Risk—0
Lund jet images from generative and cycle-consistent adversarial networksCode0
Achieving Verified Robustness to Symbol Substitutions via Interval Bound PropagationCode0
Certified Robustness to Adversarial Word SubstitutionsCode0
Combining Multi-Sequence and Synthetic Images for Improved Segmentation of Late Gadolinium Enhancement Cardiac MRI—0
STaDA: Style Transfer as Data Augmentation—0
A Geometry-Sensitive Approach for Photographic Style ClassificationCode0
It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution—0
Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation—0
Unsupervised Data Augmentation for Less-Resourced Languages with no Standardized Spelling—0
Comparing MT Approaches for Text Normalization—0
Finance document Extraction Using Data Augmentation and Attention—0
Cross-Corpus Data Augmentation for Acoustic Addressee Detection—0
Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization—0
Keep Calm and Switch On! Preserving Sentiment and Fluency in Semantic Text ExchangeCode0
Handling Syntactic Divergence in Low-resource Machine TranslationCode0
Data Augmentation with Atomic Templates for Spoken Language UnderstandingCode0
Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network—0
MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning—0
Multi-Path Learnable Wavelet Neural Network for Image Classification—0
MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation—0
Topology-preserving augmentation for CNN-based segmentation of congenital heart defects from 3D paediatric CMR—0
Depth-wise separable convolutions and multi-level pooling for an efficient spatial CNN-based steganalysis—0
Dialog State Tracking with Reinforced Data Augmentation—0
InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-PastingCode0
Two-Staged Acoustic Modeling Adaption for Robust Speech Recognition by the Example of German Oral History Interviews—0
A Kings Ransom for Encryption: Ransomware Classification using Augmented One-Shot Learning and Bayesian ApproximationCode0
Multi-step Cascaded Networks for Brain Tumor SegmentationCode0
Adaptive Regularization of Labels—0
Isotropy Maximization Loss and Entropic Score: Accurate, Fast, Efficient, Scalable, and Turnkey Neural Networks Out-of-Distribution Detection Based on The Principle of Maximum EntropyCode1
On The Evaluation of Machine Translation Systems Trained With Back-TranslationCode0
Recognition of Ischaemia and Infection in Diabetic Foot Ulcers: Dataset and Techniques—0
Generalizing Deep Whole Brain Segmentation for Pediatric and Post-Contrast MRI with Augmented Transfer Learning—0
Conditional Generative Adversarial Networks for Data Augmentation and Adaptation in Remotely Sensed Imagery—0
Sim-to-Real Learning for Casualty Detection from Ground Projected Point Cloud Data—0
SkrGAN: Sketching-rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis—0
Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks—0
Greedy AutoAugmentCode0
Learning to combine primitive skills: A step towards versatile robotic manipulationCode1
Baidu Neural Machine Translation Systems for WMT19—0
Robustifying deep networks for image segmentation—0
GANs 'N Lungs: improving pneumonia prediction—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
Fill the GAP: Exploiting BERT for Pronoun ResolutionCode0
Show:102550
← PrevPage 151 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