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 47014750 of 8378 papers

TitleStatusHype
Harnessing Hard Mixed Samples with Decoupled Regularizer0
WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses0
Build a Robust QA System with Transformer-based Mixture of ExpertsCode0
Partitioning Image Representation in Contrastive Learning0
A Novel Transparency Strategy-based Data Augmentation Approach for BI-RADS Classification of Mammograms0
Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions0
Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language ModelCode0
Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition0
Practical Recommendations for Replay-based Continual Learning Methods0
Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation0
Sparse Fuse Dense: Towards High Quality 3D Detection with Depth CompletionCode2
SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning0
DocXClassifier: High Performance Explainable Deep Network for Document Image ClassificationCode1
Type-Driven Multi-Turn Corrections for Grammatical Error CorrectionCode0
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data AugmentationCode1
MotionAug: Augmentation with Physical Correction for Human Motion PredictionCode1
Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time SeriesCode1
Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive EvaluationCode0
Understanding robustness and generalization of artificial neural networks through Fourier masksCode0
Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation0
A Squeeze-and-Excitation and Transformer based Cross-task System for Environmental Sound Recognition0
What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study0
Better Quality Estimation for Low Resource Corpus Mining0
AUCO ResNet: an end-to-end network for Covid-19 pre-screening from cough and breathCode1
Implicit field supervision for robust non-rigid shape matchingCode1
Can Synthetic Translations Improve Bitext Quality?0
Augmenting Document Representations for Dense Retrieval with Interpolation and PerturbationCode1
Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness0
Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification0
Multigrid-augmented deep learning preconditioners for the Helmholtz equation0
On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency0
Self-Promoted Supervision for Few-Shot TransformerCode1
Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech0
CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data0
Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound0
GRAND+: Scalable Graph Random Neural NetworksCode1
MDT-Net: Multi-domain Transfer by Perceptual Supervision for Unpaired Images in OCT Scan0
A survey of underwater acoustic data classification methods using deep learning for shoreline surveillance0
GSDA: Generative Adversarial Network-based Semi-Supervised Data Augmentation for Ultrasound Image Classification0
Neuromorphic Data Augmentation for Training Spiking Neural NetworksCode1
Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations0
Towards Self-Supervised Learning of Global and Object-Centric RepresentationsCode0
A Survey of Surface Defect Detection of Industrial Products Based on A Small Number of Labeled Data0
ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRICode1
Deep AutoAugmentCode1
ReF -- Rotation Equivariant Features for Local Feature Matching0
Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework0
IAE-Net: Integral Autoencoders for Discretization-Invariant LearningCode0
Deep Convolutional Neural Network for Roadway Incident Surveillance Using Audio Data0
What Matters For Meta-Learning Vision Regression Tasks?Code1
Show:102550
← PrevPage 95 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