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 77517800 of 8378 papers

TitleStatusHype
Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data0
Imbalanced Sentiment Classification Enhanced with Discourse Marker0
Addressing Model Vulnerability to Distributional Shifts over Image Transformation SetsCode0
Bias Correction of Learned Generative Models via Likelihood-free Importance Weighting0
Understanding Unconventional Preprocessors in Deep Convolutional Neural Networks for Face Identification0
Augmented Ultrasonic Data for Machine LearningCode1
Parallel Recurrent Data Augmentation for GAN training with Limited and Diverse Data0
f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning0
Data Augmentation for Rumor Detection Using Context-Sensitive Neural Language Model With Large-Scale Credibility Corpus0
Data for free: Fewer-shot algorithm learning with parametricity data augmentation0
Exploiting Synthetically Generated Data with Semi-Supervised Learning for Small and Imbalanced Datasets0
Data Augmentation for Bayesian Deep Learning0
Data Augmentation via Dependency Tree Morphing for Low-Resource LanguagesCode0
Low Resource Text Classification with ULMFit and BacktranslationCode0
Seeing is Not Necessarily Believing: Limitations of BigGANs for Data Augmentation0
Data Augmentation for Leaf Segmentation and Counting Tasks in Rosette Plants0
Reconstructing neuronal anatomy from whole-brain images0
Hyperspectral Data Augmentation0
Cleaning tasks knowledge transfer between heterogeneous robots: a deep learning approach0
End-To-End Speech Recognition Using A High Rank LSTM-CTC Based ModelCode0
Manifold Mixup improves text recognition with CTC lossCode1
Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response FunctionsCode1
Exploit fully automatic low-level segmented PET data for training high-level deep learning algorithms for the corresponding CT data0
Prostate Segmentation from 3D MRI Using a Two-Stage Model and Variable-Input Based Uncertainty Measure0
Deep Neural Network and Data Augmentation Methodology for off-axis iris segmentation in wearable headsets0
Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN0
SPDA: Superpixel-based Data Augmentation for Biomedical Image Segmentation0
Realistic Ultrasonic Environment Simulation Using Conditional Generative Adversarial Networks0
Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation0
Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images0
LaSO: Label-Set Operations networks for multi-label few-shot learningCode0
Data augmentation using learned transformations for one-shot medical image segmentationCode0
Convolutional Neural Networks for Automatic Meter Reading0
TBNet:Pulmonary Tuberculosis Diagnosing System using Deep Neural Networks0
U-NetPlus: A Modified Encoder-Decoder U-Net Architecture for Semantic and Instance Segmentation of Surgical InstrumentCode0
An Effective Hit-or-Miss Layer Favoring Feature Interpretation as Learned Prototypes Deformations0
ComplexFace: a Multi-Representation Approach for Image Classification with Small Dataset0
Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology0
Data augmentation for low resource sentiment analysis using generative adversarial networks0
Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform0
Combination of Domain Knowledge and Deep Learning for Sentiment Analysis of Short and Informal Messages on Social Media0
Asymptotically exact data augmentation: models, properties and algorithms0
MultiGrain: a unified image embedding for classes and instancesCode0
Post-Data Augmentation to Improve Deep Pose Estimation of Extreme and Wild MotionsCode0
Semi-Supervised and Task-Driven Data AugmentationCode1
Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving0
Generative Image Translation for Data Augmentation of Bone Lesion Pathology0
Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks0
EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification TasksCode2
Cross-modality (CT-MRI) prior augmented deep learning for robust lung tumor segmentation from small MR datasets0
Show:102550
← PrevPage 156 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