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 5551–5600 of 8378 papers

TitleStatusHype
Controller-Guided Partial Label Consistency Regularization with Unlabeled Data—0
PDA: Progressive Data Augmentation for General Robustness of Deep Neural Networks—0
Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completion—0
Towards physiology-informed data augmentation for EEG-based BCIs—0
Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learning—0
Towards Precision Cardiovascular Analysis in Zebrafish: The ZACAF Paradigm—0
Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation—0
Towards Reducing Aleatoric Uncertainty for Medical Imaging Tasks—0
Towards Reversal-Based Textual Data Augmentation for NLI Problems with Opposable Classes—0
Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild—0
Towards Robust Aspect-based Sentiment Analysis through Non-counterfactual Augmentations—0
Towards Robust Deep Neural Networks with BANG—0
Towards Robust Human Activity Recognition from RGB Video Stream with Limited Labeled Data—0
Towards Robust Partially Supervised Multi-Structure Medical Image Segmentation on Small-Scale Data—0
Towards Robustness and Diversity: Continual Learning in Dialog Generation with Text-Mixup and Batch Nuclear-Norm Maximization—0
Towards Robustness of Neural Networks—0
Towards Robust Neural Networks with Lipschitz Continuity—0
Towards Robust Neural Retrieval with Source Domain Synthetic Pre-Finetuning—0
Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems—0
Towards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches—0
Towards Robust Point Cloud Models with Context-Consistency Network and Adaptive Augmentation—0
Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution—0
Towards Robust Waveform-Based Acoustic Models—0
Towards Santali Linguistic Inclusion: Building the First Santali-to-English Translation Model using mT5 Transformer and Data Augmentation—0
Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa—0
Towards Summarizing Healthcare Questions in Low-Resource Setting—0
Towards the Imagenets of ML4EDA—0
Towards Understanding of Frequency Dependence on Sound Event Detection—0
Towards Understanding the Generalization of Medical Text-to-SQL Models and Datasets—0
Towards Understanding Why Data Augmentation Improves Generalization—0
Towards Visible and Thermal Drone Monitoring with Convolutional Neural Networks—0
Towards Zero-Label Language Learning—0
Toxicity Detection can be Sensitive to the Conversational Context—0
Track, Check, Repeat: An EM Approach to Unsupervised Tracking—0
DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks—0
Tracking e-cigarette warning label compliance on Instagram with deep learning—0
TractoFormer: A Novel Fiber-level Whole Brain Tractography Analysis Framework Using Spectral Embedding and Vision Transformers—0
Tradeoffs in Data Augmentation: An Empirical Study—0
Traffic Context Aware Data Augmentation for Rare Object Detection in Autonomous Driving—0
TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors—0
A systematic approach to random data augmentation on graph neural networks—0
Training Augmentation with Adversarial Examples for Robust Speech Recognition—0
Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild—0
Training Data Augmentation for Deep Learning Radio Frequency Systems—0
Training Data Augmentation for Detecting Adverse Drug Reactions in User-Generated Content—0
Training Data Augmentation for Low-Resource Morphological Inflection—0
Training Deep Learning Models with Hybrid Datasets for Robust Automatic Target Detection on real SAR images—0
Training Deep Neural Classifiers with Soft Diamond Regularizers—0
Training-free Camera Control for Video Generation—0
Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator—0
Show:102550
← PrevPage 112 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