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 2951–3000 of 8378 papers

TitleStatusHype
Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary EnvironmentCode0
Data Augmentation to Improve Large Language Models in Food Hazard and Product DetectionCode0
Automatic Data Augmentation via Invariance-Constrained LearningCode0
Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in SummarizationCode0
FloMo: Tractable Motion Prediction with Normalizing FlowsCode0
Fully Automatic and Real-Time Catheter Segmentation in X-Ray FluoroscopyCode0
Data augmentation through multivariate scenario forecasting in Data Centers using Generative Adversarial NetworksCode0
Data Augmentation Through Monte Carlo Arithmetic Leads to More Generalizable Classification in ConnectomicsCode0
Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation LearningCode0
Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological ImagesCode0
Chameleon: Foundation Models for Fairness-aware Multi-modal Data Augmentation to Enhance Coverage of MinoritiesCode0
Adversarial Word Dilution as Text Data Augmentation in Low-Resource RegimeCode0
Flareon: Stealthy any2any Backdoor Injection via Poisoned AugmentationCode0
Action Recognition Using Volumetric Motion RepresentationsCode0
Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference ModelsCode0
Analyzing Data Augmentation for Medical Images: A Case Study in Ultrasound ImagesCode0
Data Augmentation Techniques for Cross-Domain WiFi CSI-based Human Activity RecognitionCode0
Promptable Counterfactual Diffusion Model for Unified Brain Tumor Segmentation and Generation with MRIsCode0
Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental LearningCode0
Enhancing human action recognition with GAN-based data augmentationCode0
Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathologyCode0
Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex OptimizationCode0
Neural Network Robustness as a Verification Property: A Principled Case StudyCode0
Enhancing Lesion Segmentation in PET/CT Imaging with Deep Learning and Advanced Data Preprocessing TechniquesCode0
Noise-Agnostic Quantum Error Mitigation with Data Augmented Neural ModelsCode0
Data Augmentation Techniques for Chinese Disease Name NormalizationCode0
FiNLP at FinCausal 2020 Task 1: Mixture of BERTs for Causal Sentence Identification in Financial TextsCode0
Enhancing Masked Time-Series Modeling via Dropping PatchesCode0
Fine Tuning vs. Retrieval Augmented Generation for Less Popular KnowledgeCode0
First-Order Manifold Data Augmentation for Regression LearningCode0
On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language ProcessingCode0
Character-level HyperNetworks for Hate Speech DetectionCode0
Automatic Data Augmentation by Learning the Deterministic PolicyCode0
Data augmentation on-the-fly and active learning in data stream classificationCode0
Data augmentation on graphs for table type classificationCode0
Flexible framework for generating synthetic electrocardiograms and photoplethysmogramsCode0
Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR ImagesCode0
Automatic Configuration of Deep Neural Networks with EGOCode0
AugGPT: Leveraging ChatGPT for Text Data AugmentationCode0
QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive AdaptationCode0
Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep ChemometricsCode0
Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy InterpolationCode0
FilipN@LT-EDI-ACL2022-Detecting signs of Depression from Social Media: Examining the use of summarization methods as data augmentation for text classificationCode0
Few-shot learning through contextual data augmentationCode0
Automatic Classification of Attributes in German Adjective-Noun PhrasesCode0
Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy ClassificationCode0
ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMsCode0
Enhancing Robustness of AI Offensive Code Generators via Data AugmentationCode0
Few-shot learning via tensor hallucinationCode0
Automatic classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray image: combination of data augmentation methodsCode0
Show:102550
← PrevPage 60 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