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 54515500 of 8378 papers

TitleStatusHype
Data Augmentation Strategies for Improving Sequential Recommender Systems0
Impact of Dataset on Acoustic Models for Automatic Speech Recognition0
Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalizationCode0
SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph DistanceCode0
A Method of Data Augmentation to Train a Small Area Fingerprint Recognition Deep Neural Network with a Normal Fingerprint Database0
Prompt-based System for Personality and Interpersonal Reactivity Prediction0
Transformer-based Multimodal Information Fusion for Facial Expression Analysis0
A Novel Framework for Assessment of Learning-based Detectors in Realistic Conditions with Application to Deepfake Detection0
A New Approach to Improve Learning-based Deepfake Detection in Realistic Conditions0
Mask Usage Recognition using Vision Transformer with Transfer Learning and Data Augmentation0
Generative Modeling Helps Weak Supervision (and Vice Versa)Code0
Conditional Generative Data Augmentation for Clinical Audio Datasets0
Improving Neural Predictivity in the Visual Cortex with Gated Recurrent Connections0
WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses0
Harnessing Hard Mixed Samples with Decoupled Regularizer0
A Novel Transparency Strategy-based Data Augmentation Approach for BI-RADS Classification of Mammograms0
Build a Robust QA System with Transformer-based Mixture of ExpertsCode0
Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions0
Partitioning Image Representation in Contrastive Learning0
Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language ModelCode0
Practical Recommendations for Replay-based Continual Learning Methods0
Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition0
SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning0
Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation0
Type-Driven Multi-Turn Corrections for Grammatical Error CorrectionCode0
A Squeeze-and-Excitation and Transformer based Cross-task System for Environmental Sound Recognition0
Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation0
Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive EvaluationCode0
What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study0
Understanding robustness and generalization of artificial neural networks through Fourier masksCode0
Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification0
Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness0
Better Quality Estimation for Low Resource Corpus Mining0
Can Synthetic Translations Improve Bitext Quality?0
On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency0
Multigrid-augmented deep learning preconditioners for the Helmholtz equation0
CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data0
Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech0
Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound0
MDT-Net: Multi-domain Transfer by Perceptual Supervision for Unpaired Images in OCT Scan0
Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations0
Towards Self-Supervised Learning of Global and Object-Centric RepresentationsCode0
GSDA: Generative Adversarial Network-based Semi-Supervised Data Augmentation for Ultrasound Image Classification0
A Survey of Surface Defect Detection of Industrial Products Based on A Small Number of Labeled Data0
A survey of underwater acoustic data classification methods using deep learning for shoreline surveillance0
IAE-Net: Integral Autoencoders for Discretization-Invariant LearningCode0
ReF -- Rotation Equivariant Features for Local Feature Matching0
Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework0
Deep Convolutional Neural Network for Roadway Incident Surveillance Using Audio Data0
Towards Efficient Data-Centric Robust Machine Learning with Noise-based Augmentation0
Show:102550
← PrevPage 110 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