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 68016850 of 8378 papers

TitleStatusHype
An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances0
Paying Per-label Attention for Multi-label Extraction from Radiology Reports0
An Empirical Survey of Data Augmentation for Time Series Classification with Neural NetworksCode1
Robust Retinal Vessel Segmentation from a Data Augmentation Perspective0
A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks0
Learning from Few Samples: A Survey0
Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction0
Reliable Tuberculosis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization0
KOVIS: Keypoint-based Visual Servoing with Zero-Shot Sim-to-Real Transfer for Robotics ManipulationCode1
ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and ExplanationCode1
Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identificationCode1
Normal-bundle BootstrapCode0
Semi-Supervised Learning with Data Augmentation for End-to-End ASR0
Part-Aware Data Augmentation for 3D Object Detection in Point CloudCode1
Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing0
Representation Learning with Video Deep InfoMax0
Self-supervised Learning for Large-scale Item Recommendations0
Robust and Generalizable Visual Representation Learning via Random ConvolutionsCode1
Counting Fish and Dolphins in Sonar Images Using Deep Learning0
Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View SetupCode1
SeismoFlow -- Data augmentation for the class imbalance problem0
How Does Data Augmentation Affect Privacy in Machine Learning?Code0
CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution LayersCode1
Regularizing Deep Networks with Semantic Data AugmentationCode1
Investigating Bias and Fairness in Facial Expression Recognition0
Multimodal Dialogue State Tracking By QA Approach with Data Augmentation0
Semantic Equivalent Adversarial Data Augmentation for Visual Question AnsweringCode1
On regularization of gradient descent, layer imbalance and flat minima0
Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation0
OnlineAugment: Online Data Augmentation with Less Domain KnowledgeCode1
Surface Normal Estimation of Tilted Images via Spatial RectifierCode1
2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge0
Uncertainty Quantification and Deep EnsemblesCode1
FeatMatch: Feature-Based Augmentation for Semi-Supervised LearningCode1
Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation0
Towards Evaluating Driver Fatigue with Robust Deep Learning Models0
Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data AugmentationCode1
Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and EnsembleCode1
The Notary in the Haystack -- Countering Class Imbalance in Document Processing with CNNs0
Tracking Passengers and Baggage Items using Multi-camera Systems at Security CheckpointsCode0
How to trust unlabeled data? Instance Credibility Inference for Few-Shot LearningCode1
An Ensemble of Convolutional Neural Networks for Audio Classification0
ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised LearningCode1
Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR0
A Machine Learning Approach to Assess Student Group Collaboration Using Individual Level Behavioral Cues0
Data-Efficient Reinforcement Learning with Self-Predictive RepresentationsCode1
The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results0
An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter OptimizationCode1
Complex Wavelet SSIM based Image Data Augmentation0
M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification0
Show:102550
← PrevPage 137 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 2×96d) (Faster AA)Percentage error2Unverified
5Shake-Shake (26 2×112d) (Faster AA)Percentage error2Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7Unverified
2PaCMAPClassification Accuracy85.3Unverified
3hNNEClassification Accuracy77.4Unverified
4TopoAEClassification Accuracy74.6Unverified