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 7651–7700 of 8378 papers

TitleStatusHype
Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces—0
Combining Noise-to-Image and Image-to-Image GANs: Brain MR Image Augmentation for Tumor Detection—0
Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence—0
Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss FunctionCode0
Learning the Non-linearity in Convolutional Neural Networks—0
Data Augementation with Polya Inverse Gamma—0
Implicit Rugosity Regularization via Data Augmentation—0
Compositional pre-training for neural semantic parsing—0
XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering—0
On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural NetworksCode0
Style transfer-based image synthesis as an efficient regularization technique in deep learning—0
Straight to Shapes++: Real-time Instance Segmentation Made More AccurateCode0
Soft Contextual Data Augmentation for Neural Machine TranslationCode0
Contextual Out-of-Domain Utterance Handling With Counterfeit Data AugmentationCode0
Mask-Guided Portrait Editing with Conditional GANs—0
Pose estimator and tracker using temporal flow maps for limbs—0
Augmenting correlation structures in spatial data using deep generative modelsCode0
Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data AugmentationCode0
Augmenting Data with Mixup for Sentence Classification: An Empirical StudyCode0
Exploring Bias in GAN-based Data Augmentation for Small Samples—0
Robust sound event detection in bioacoustic sensor networksCode0
Human Vocal Sentiment Analysis—0
Fast classification of small X-ray diffraction datasets using data augmentation and deep neural networksCode0
Online Hyper-parameter Learning for Auto-Augmentation StrategyCode1
LiDAR Sensor modeling and Data augmentation with GANs for Autonomous drivingCode0
Biosignal Generation and Latent Variable Analysis with Recurrent Generative Adversarial Networks—0
A Meta Understanding of Meta-Learning—0
PAGANDA: An Adaptive Task-Independent Automatic Data AugmentationCode0
How is Gaze Influenced by Image Transformations? Dataset and ModelCode1
Non-Parametric Priors For Generative Adversarial Networks—0
ROI Regularization for Semi-supervised and Supervised Learning—0
Population Based Augmentation: Efficient Learning of Augmentation Policy SchedulesCode0
Data augmentation in microscopic images for material data mining—0
Two-Stage Convolutional Neural Network Architecture for Lung Nodule Detection—0
Does Data Augmentation Lead to Positive Margin?—0
Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification TasksCode0
Accurate Face Detection for High Performance—0
Drone Path-Following in GPS-Denied Environments using Convolutional NetworksCode0
A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling—0
Intra-clip Aggregation for Video Person Re-identification—0
Deep Convolutional Neural Network-Based Autonomous Drone Navigation—0
A Survey on Neural Architecture Search—0
SoilingNet: Soiling Detection on Automotive Surround-View Cameras—0
Leveraging Crowdsourced GPS Data for Road Extraction from Aerial Imagery—0
Anti-Confusing: Region-Aware Network for Human Pose Estimation—0
Fast AutoAugmentCode1
Learn to synthesize and synthesize to learnCode0
A quantifiable testing of global translational invariance in Convolutional and Capsule Networks—0
Improving machine classification using human uncertainty measurements—0
Improved resistance of neural networks to adversarial images through generative pre-training—0
Show:102550
← PrevPage 154 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